{"count":2908,"results":[{"created_at":"2026-11-05T19:45:55.972644+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":126,"model_responses":128,"native_controls":883,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"b2-full-round-20261105-enospc-retry1-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/b2-full-round-20261105-enospc-retry1-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-11-05T15:44:00.497752+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":254,"model_responses":258,"native_controls":1165,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"b2-full-round-20261105-initretry1-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/b2-full-round-20261105-initretry1-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-11-05T13:25:34.205598+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":118,"model_responses":119,"native_controls":588,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"b2-full-round-20261105-initretry1-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/b2-full-round-20261105-initretry1-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-11-05T15:09:51.090722+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":121,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"b2-full-round-20261105-storage-retry1-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/b2-full-round-20261105-storage-retry1-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-05T16:31:59.137417+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":97,"native_controls":971,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"b2-full-round-20261105-storage-retry1-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/b2-full-round-20261105-storage-retry1-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-11-05T16:29:17.879889+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":686,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"b2-full-round-20261105-storage-retry1-initretry1-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/b2-full-round-20261105-storage-retry1-initretry1-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-11-05T16:25:31.626725+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":166,"model_responses":168,"native_controls":620,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"b2-full-round-20261105-storage-retry1-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/b2-full-round-20261105-storage-retry1-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-11-05T14:42:36.474808+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":380,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"b2-full-round-20261105-storage-retry1-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/b2-full-round-20261105-storage-retry1-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-27T16:03:36.804550+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":348,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-27T15:47:45.304960+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":330,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-27T16:13:23.040071+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":385,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sam300-20261027T225000-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sam300-20261027T225000-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-27T17:59:11.791366+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":89,"native_controls":1075,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-27T18:12:57.196363+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":927,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-27T20:57:17.340866+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":989,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-27T18:43:58.221823+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":397,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-27T18:47:42.723559+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1308,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-27T18:52:14.487292+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1371,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-27T21:03:52.387741+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":1248,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-27T17:47:55.981717+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":90,"native_controls":415,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-27T17:30:44.379737+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":85,"native_controls":487,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-27T19:52:58.265490+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":99,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-27T19:45:45.675458+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":368,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-27T18:31:47.327843+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":381,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-27T19:26:36.866573+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":333,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-followup17-sim51-20261027T234500-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-followup17-sim51-20261027T234500-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-28T04:02:19.949831+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":342,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda-human-retry15-complete-20261028T112000-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda-human-retry15-complete-20261028T112000-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-26T08:38:29.944443+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":64,"native_controls":192,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-extra-six-graphics-20261026-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-extra-six-graphics-20261026-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-26T10:37:41.190803+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":null,"native_controls":484,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-extra-six-graphics-20261026-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-extra-six-graphics-20261026-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-26T08:00:54.331814+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":16,"model_responses":17,"native_controls":102,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-extra-six-graphics-20261026-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-extra-six-graphics-20261026-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-26T09:29:22.726741+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":null,"native_controls":540,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-extra-six-graphics-20261026-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-extra-six-graphics-20261026-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-26T10:44:14.388162+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":null,"native_controls":379,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-extra-six-graphics-20261026-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-extra-six-graphics-20261026-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-26T08:27:05.584731+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":33,"native_controls":172,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-final-six-20261026-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-final-six-20261026-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-26T11:52:12.731863+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":null,"native_controls":557,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-final-six-20261026-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-final-six-20261026-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-26T09:49:23.656580+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":null,"native_controls":180,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-final-six-20261026-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-final-six-20261026-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-26T10:19:13.445226+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":92,"native_controls":540,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-final-six-20261026-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-final-six-20261026-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-26T12:39:20.043733+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":117,"native_controls":396,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-final-six-20261026-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-final-six-20261026-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-26T12:55:56.415887+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":93,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-hilbert11-20261026T191600-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-hilbert11-20261026T191600-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-26T10:28:47.693490+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":45,"native_controls":315,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-hilbert13-20261026-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-hilbert13-20261026-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-26T07:32:57.168260+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":43,"native_controls":189,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-single-gpu-20261026-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-single-gpu-20261026-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-26T09:02:41.159990+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":775,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-single-gpu-20261026-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-single-gpu-20261026-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-26T07:14:15.662851+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":23,"native_controls":96,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-single-gpu-20261026-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-single-gpu-20261026-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-26T08:07:12.366559+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":null,"native_controls":622,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-single-gpu-20261026-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-single-gpu-20261026-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-26T07:31:52.236467+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":44,"native_controls":261,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-single-gpu-20261026-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-single-gpu-20261026-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-26T08:50:42.966813+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":117,"native_controls":278,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-single-gpu-20261026-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-single-gpu-20261026-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-27T06:37:01.647753+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":11,"native_controls":71,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-refill16-20261027T141000-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-refill16-20261027T141000-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-27T06:53:49.662925+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-refill16-20261027T141000-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-refill16-20261027T141000-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-27T11:16:31.475281+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-27T11:46:58.227778+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":166,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-27T12:21:12.523874+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":139,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-27T12:55:11.214560+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":718,"native_terminal":true,"score":0.05,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-27T12:37:01.411756+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":87,"native_controls":659,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-27T14:06:34.708645+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":80,"native_controls":582,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-27T11:41:40.823259+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":109,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-27T13:14:13.508681+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":137,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-27T11:38:17.838931+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":472,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-27T12:42:08.706739+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":486,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-27T12:33:07.688579+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":419,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-27T13:52:42.191159+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":486,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-27T11:53:22.026239+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":429,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-27T12:38:34.140185+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":377,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-18T08:27:37.498801+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":98,"native_controls":772,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-18T10:06:54.531860+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":899,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-18T09:58:45.482969+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":717,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-18T09:16:07.236690+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":898,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-18T08:44:18.446723+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1039,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-18T10:08:11.600763+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":1017,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:45:21.198372+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":567,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-18T08:24:23.955276+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":101,"native_controls":1024,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-18T08:21:49.910167+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":90,"native_controls":912,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-18T08:47:25.154090+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":481,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-17T05:29:04.184314+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":692,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:37:30.865810+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":563,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-17T04:36:16.482530+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":372,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-21T11:06:34.418193+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:02:53.585626+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-21T11:10:22.441970+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-21T11:08:51.942853+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":440,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-21T10:46:11.377303+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":322,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-21T10:46:52.164149+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":346,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:10:46.118678+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":11,"native_controls":90,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-21T10:54:57.930753+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-21T10:53:31.989377+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":600,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:05:26.778458+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":549,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-21T10:52:57.278098+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":336,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-p50supp1-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-p50supp1-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-18T10:16:27.163869+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1208,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-18T09:12:44.044011+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1206,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-18T09:14:52.100158+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":1146,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-18T08:35:04.875131+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":391,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:37:14.354232+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-18T09:15:18.636444+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":16,"model_responses":16,"native_controls":206,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-18T09:17:49.724089+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":333,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-18T09:08:13.724538+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":455,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:40:02.833150+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":395,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-17T04:58:38.455351+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":143,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-18T08:20:14.302718+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":61,"native_controls":648,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-18T08:24:12.140375+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-18T08:08:58.659242+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":61,"native_controls":417,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-18T09:02:24.913260+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":685,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-18T09:06:22.301909+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":800,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-17T04:51:08.263836+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-17T04:53:55.897119+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":336,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-17T04:39:25.984183+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":399,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261017-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261017-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-22T15:07:15.070005+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-22T15:09:09.335504+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1100,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-22T14:45:05.551637+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":73,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-22T14:52:53.823285+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":168,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-22T15:14:42.861015+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1600,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-22T14:51:13.381182+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":238,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-22T14:59:59.491370+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":410,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-22T15:05:44.493344+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":436,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-22T14:41:46.810037+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":361,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-random-s0-scene1.json"},{"created_at":"2026-10-22T14:49:32.774734+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":600,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-22T14:46:13.620420+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":395,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-22T23:34:09.007806+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-22T23:27:39.959380+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":518,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-22T23:45:39.213807+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1613,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-22T23:36:01.785638+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":1475,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-22T23:36:07.468543+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":1410,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-22T23:33:58.348420+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-22T23:30:43.467877+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":389,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-22T23:29:51.505595+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-22T23:29:32.921962+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":341,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-22T23:21:55.738364+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-22T23:25:47.839850+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":371,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-22T23:25:30.738975+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":386,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-22T14:58:01.480645+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":220,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-22T15:02:13.169569+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-22T15:06:51.972925+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":199,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-22T14:54:06.907109+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":741,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dev23-horizon-medium-20261022-p50supp1-rerun27-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-horizon-medium-20261022-p50supp1-rerun27-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:50:03.402396+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":597,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-18T09:37:20.187108+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":688,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:43:39.343268+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-18T08:43:36.000773+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":990,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-18T08:50:40.357269+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-18T10:21:15.287288+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":1098,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-18T08:12:40.024003+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":365,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-17T04:59:08.822443+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":517,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:36:22.366552+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":567,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-17T04:38:51.987782+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":377,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-18T09:38:07.189159+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":1190,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-18T08:46:39.379023+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":86,"native_controls":1296,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-18T09:10:14.127831+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":1153,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:42:44.238962+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":338,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-18T09:29:17.649586+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":436,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-18T08:58:44.471092+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":460,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-18T08:22:48.221140+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:29:24.739645+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":319,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-17T04:55:03.914939+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":7,"model_responses":7,"native_controls":71,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:36:39.251284+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":302,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-18T08:25:37.715378+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":417,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-push_T-random-s0-scene1.json"},{"created_at":"2026-10-18T08:17:58.705142+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":63,"native_controls":700,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-18T08:36:16.331951+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":768,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-18T09:07:44.073931+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":788,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-17T04:50:20.819085+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-17T04:39:56.539242+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":364,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-17T04:49:00.523519+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261017-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261017-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-23T03:28:08.143736+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-23T03:26:51.015732+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-23T03:22:27.142429+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":172,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-23T03:46:15.120843+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-23T03:41:12.592148+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-23T03:45:44.108215+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":1100,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-23T03:36:49.297186+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":488,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-23T03:42:06.704778+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":580,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-23T03:40:44.567909+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":644,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:03:08.495827+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":1202,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-23T04:06:09.410600+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":94,"native_controls":1653,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-23T04:15:10.304174+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1820,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-23T03:40:53.030650+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":295,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-23T03:38:06.165890+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":355,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-23T03:34:27.442969+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":10,"model_responses":10,"native_controls":77,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-23T03:36:59.679371+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":19,"model_responses":19,"native_controls":117,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-23T03:40:42.151428+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":167,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:09:24.862514+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":1497,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-23T04:14:14.523468+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":1582,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-23T04:08:38.779293+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":1380,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-23T03:50:32.581933+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":223,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-23T03:59:49.466924+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":537,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-23T03:56:33.608040+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":256,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:10:44.568184+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-23T04:13:09.609757+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-23T04:13:56.244594+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:03:55.034663+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":357,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-23T04:05:54.818080+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":346,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:03:41.846834+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":321,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-23T04:11:46.798764+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":362,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-23T04:26:16.200746+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-23T05:14:31.650941+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":551,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-23T04:14:14.202955+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":190,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-23T04:18:56.331256+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-23T04:18:23.689704+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":195,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:42:35.316433+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":939,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-23T04:21:30.912916+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":317,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-23T04:51:22.741924+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":961,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-23T04:26:52.294173+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":345,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-23T04:30:00.963872+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":358,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-23T04:28:55.029627+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":376,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:46:29.124674+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":678,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dev23-sequence-medium-20261023-p50supp1-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dev23-sequence-medium-20261023-p50supp1-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:26:36.844906+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":145,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:51:13.033206+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":774,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-16T17:27:10.051954+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":932,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:04:40.742457+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":954,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:03:25.449492+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:33:58.158237+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":774,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:51:02.527642+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":251,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:38:47.294292+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1387,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:05:08.974479+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":688,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:04:01.401327+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":1100,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-16T15:45:09.821058+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":339,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-16T18:26:09.709553+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":93,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:24:06.795291+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":766,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-16T18:58:20.097308+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":1450,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:22:20.081810+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":300,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:05:50.929007+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":498,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:17:54.039274+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":435,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:19:32.719599+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":785,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-16T17:13:21.746177+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":319,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:22:59.366193+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":960,"native_terminal":true,"score":0.75,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:16:26.977859+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1043,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-16T18:12:36.083998+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":455,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:23:51.643399+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":420,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:20:06.808744+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":819,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:42:07.121253+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":278,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:12:02.724685+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":326,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:30:58.466258+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":242,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-16T19:10:45.648268+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T15:44:34.273544+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-16T18:16:32.088625+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:55:14.319200+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":286,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-push_T-random-s0-scene0.json"},{"created_at":"2026-10-16T18:06:11.032269+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:25:19.665339+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":275,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:40:36.313211+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":989,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-16T16:19:46.731137+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":474,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-16T18:44:08.219964+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T15:50:21.552694+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":334,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-16T16:54:37.148309+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":609,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-16T18:43:54.943446+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":719,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:56:38.988749+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:21:27.942220+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":418,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T15:58:07.321920+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-horizon-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":610,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-horizon-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-model-action-horizon","score_scale":"0..1"},"run_id":"dual42-horizon-medium-20261016-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-horizon-medium-20261016-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-16T17:52:37.602876+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":198,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:01:52.595812+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":1050,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-16T17:29:19.194036+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":94,"native_controls":1038,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:01:41.713307+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:49:37.701519+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":926,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:11:07.403483+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":571,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:06:18.572203+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":286,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:32:13.590036+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1161,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:02:21.979140+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:06:22.790297+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":923,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-16T15:47:45.013735+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":304,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-16T18:26:32.363767+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":145,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:01:12.545316+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":692,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-16T19:10:01.640597+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":1493,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:59:54.378565+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":286,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:04:51.277559+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:37:50.993411+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":580,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:19:14.289240+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":769,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-16T17:18:52.056325+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:40:20.121602+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":1000,"native_terminal":true,"score":0.75,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:19:05.731603+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":1240,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-16T18:51:17.749534+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":298,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:29:27.112715+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:18:34.480043+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1014,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:31:00.350456+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":761,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:14:09.334917+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":351,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-16T16:27:02.809950+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":19,"model_responses":19,"native_controls":148,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-16T19:34:56.040426+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T15:36:42.490973+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":233,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-16T18:11:54.326198+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":331,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:02:21.181787+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":412,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-push_T-random-s0-scene0.json"},{"created_at":"2026-10-16T17:50:00.801242+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:31:41.399209+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":293,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:56:39.623067+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":1035,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-16T16:11:22.018986+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":441,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-16T18:21:13.013432+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":319,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T15:53:30.041193+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":518,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-16T16:50:47.308963+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":595,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-16T18:38:42.988741+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":900,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-16T18:42:17.860454+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-16T17:20:59.934182+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":439,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T15:50:36.738755+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"dual42-sequence-medium-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":621,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"dual42-sequence-medium-20261016","max_decisions":100,"native_control_cap":null,"profile":"custom-eef-sequence","score_scale":"0..1"},"run_id":"dual42-sequence-medium-20261016-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/dual42-sequence-medium-20261016-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-11-02T14:52:05.802919+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":146,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-02T14:55:20.449208+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":189,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-02T15:01:51.113538+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-02T15:14:20.299019+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":662,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-11-02T15:15:55.271406+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":780,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-11-02T15:03:11.269041+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":387,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:17:52.393929+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":1056,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:25:23.831378+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":999,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-11-02T15:23:09.940673+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":937,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-11-02T15:45:36.789618+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":1031,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:40:40.407716+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1078,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-02T15:45:17.354692+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1056,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-02T15:33:27.838610+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":560,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:01:27.896206+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":614,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-02T15:43:11.986712+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":439,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:03:05.955585+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":768,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:15:48.007918+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1425,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:20:36.630912+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1124,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-11-02T15:59:11.091406+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":297,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-11-02T15:58:33.959037+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":409,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-11-02T16:03:12.119330+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":294,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:02:44.063199+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":83,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:07:13.950517+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":144,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:10:08.753752+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":130,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:37:36.290268+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":1428,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:32:17.659605+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":1451,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:45:56.137562+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":1399,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:26:17.723636+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":519,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:23:16.419225+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":286,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:29:55.575819+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":472,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:01:47.895569+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1079,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-11-02T16:56:59.564848+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1148,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-11-02T16:55:48.245697+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":684,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:43:51.873845+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":282,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:54:18.025415+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":535,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:49:47.869855+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":330,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:04:04.100240+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":457,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:12:52.323761+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:15:13.400210+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:14:29.057906+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":357,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:11:25.541604+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":370,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:10:40.106892+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":382,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:12:52.704668+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":326,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:11:49.642940+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":314,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:25:14.356921+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":493,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:17:31.916564+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":143,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:24:27.262228+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":377,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:23:30.659885+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":336,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:54:58.266937+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":386,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-push_T-random-s0-scene1.json"},{"created_at":"2026-11-02T17:41:03.849658+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":295,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-push_T-standard-s0-scene0.json"},{"created_at":"2026-11-02T17:42:29.810746+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":380,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-push_T-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:32:59.928297+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":532,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:42:46.682064+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:43:54.164289+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:45:22.680677+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":273,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:43:32.791359+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":287,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:52:55.298507+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-11-02T18:18:12.103844+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1028,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-11-02T18:01:45.550087+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":542,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-11-02T18:02:05.609916+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":540,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-11-02T18:03:04.416702+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-02T18:07:02.671183+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":334,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-02T18:12:11.519953+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":383,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-02T18:32:15.635387+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":764,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-11-02T18:16:07.357159+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":356,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-11-02T18:36:38.344126+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":669,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-11-02T18:19:45.306854+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-swap_T-standard-s0-scene1.json"},{"created_at":"2026-11-02T18:21:47.927755+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":351,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-swap_T-standard-s0-scene2.json"},{"created_at":"2026-11-02T18:28:03.034586+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":394,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"high-dev69-20261102-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/high-dev69-20261102-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:21:03.314610+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":173,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-17T04:51:40.931831+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":170,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-17T06:41:02.694975+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":829,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-17T09:27:51.365411+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":774,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-17T09:48:00.140013+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":500,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:11:41.340502+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":646,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:13:03.020464+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":922,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:15:48.484746+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":1063,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:20:19.594888+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":994,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:16:19.283419+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":892,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-17T09:01:12.153165+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":470,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:13:54.053938+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":547,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:34:48.763796+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":774,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-17T09:31:58.537350+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1158,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:10:49.459092+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1029,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:42:36.383085+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1335,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:32:07.898468+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":355,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-17T06:13:30.172553+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":461,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:07:05.899313+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":378,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-17T08:49:20.114508+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":11,"native_controls":72,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-17T08:51:10.444184+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":173,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:07:31.664890+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":152,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-17T06:00:54.305170+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1397,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-17T09:16:49.972436+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":1530,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-17T06:11:34.521259+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":1328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:37:46.489096+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":539,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-17T06:39:27.679121+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":427,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-17T09:13:29.506099+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":389,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:16:54.685097+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":862,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:29:27.236240+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":263,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-17T04:54:37.098312+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":303,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:25:48.068101+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":214,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-17T06:01:24.630101+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":482,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:50:30.443928+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":477,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:43:20.291640+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":398,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-17T08:58:28.198600+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":346,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-17T06:12:32.478887+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":360,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:23:06.729385+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":320,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-17T08:47:37.106424+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":6,"model_responses":6,"native_controls":58,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:43:28.863798+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":244,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-17T06:22:49.992342+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":271,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-17T09:15:19.233920+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-17T06:14:08.058294+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":363,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-17T09:00:26.809567+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":302,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-17T09:14:42.265850+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-17T08:57:20.657748+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":518,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:38:09.593755+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":624,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-17T06:03:21.692954+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":678,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:59:27.809111+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":203,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-17T05:18:41.140251+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":256,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:54:41.590371+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":205,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-17T09:32:40.099006+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":573,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-17T09:21:50.596887+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":680,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-17T09:08:40.011346+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":397,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-17T06:24:34.240788+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":399,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-17T05:50:32.718380+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":353,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-17T05:59:34.519249+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":658,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-17T06:31:07.124479+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":574,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:30:59.702927+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":737,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-17T09:28:33.347320+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":384,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-17T06:14:30.426816+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":360,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-17T06:34:49.605934+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":399,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-17T09:43:34.283298+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":189,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-restart1-20261017-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-restart1-20261017-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-17T10:03:13.494754+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":1095,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-restart1-20261017-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-restart1-20261017-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-17T09:42:48.459100+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":363,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-17T09:45:47.679036+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":379,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-17T10:10:24.560729+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":358,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-restart1-20261017-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-restart1-20261017-push_T-random-s0-scene1.json"},{"created_at":"2026-10-17T10:29:29.037222+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":446,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-restart1-20261017-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-restart1-20261017-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-17T09:55:39.747754+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":403,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-devset-restart1-20261017-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-devset-restart1-20261017-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-15T13:26:33.368248+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":180,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-15T17:33:51.422416+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":712,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-15T14:01:15.604274+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":856,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-15T14:17:31.892087+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1071,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-15T14:59:58.767052+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":807,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-15T10:52:06.025016+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":520,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-15T12:07:03.739206+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":290,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-15T13:54:41.595794+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1141,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-15T12:37:10.148556+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":582,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-15T13:48:51.726200+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":894,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-15T09:17:51.177487+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":303,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-15T09:01:24.260963+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":16,"model_responses":16,"native_controls":111,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-15T10:32:23.812902+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":418,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-15T18:19:53.618836+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":1287,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-15T09:06:39.183366+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":209,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-15T10:27:47.236106+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":468,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-15T13:53:46.366363+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":478,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-15T11:59:29.995511+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":454,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-15T12:14:53.123055+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":346,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-15T11:43:44.009535+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":647,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-15T10:44:56.714938+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":735,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-15T14:13:59.603752+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":499,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-15T12:14:56.576889+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":369,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-15T14:04:24.055438+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":718,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-15T13:05:00.739283+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":312,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-15T10:35:26.909779+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":317,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-15T10:16:46.399640+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":447,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-15T14:31:22.967644+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":704,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-15T10:27:48.997164+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-15T13:13:31.174866+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":370,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-15T15:35:57.843969+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":279,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-push_T-random-s0-scene0.json"},{"created_at":"2026-10-15T10:37:34.738318+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-15T13:25:51.937664+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":269,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-15T09:55:49.886465+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":141,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-15T09:44:43.535936+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":417,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-15T13:51:33.121677+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":374,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-15T11:59:29.294693+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":578,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-15T10:41:07.236353+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":525,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-15T15:59:24.659986+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":861,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-15T12:59:11.963069+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-15T15:42:28.675256+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":478,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-15T10:51:20.471947+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-eef-relative-cap20-medium-r1-20261015","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":666,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-eef-relative-cap20-medium-r1-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-eef-relative","score_scale":"0..1"},"run_id":"l3-eef-relative-cap20-medium-r1-20261015-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-eef-relative-cap20-medium-r1-20261015-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-12T18:44:30.425276+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":146,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:39:40.269131+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":767,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-12T19:02:08.425740+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":925,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:44:29.548082+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":941,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-13T07:17:42.568168+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-13T06:28:25.863431+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":797,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:01:37.212517+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":275,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:33:08.065601+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":970,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:13:12.184249+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":571,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:52:56.760567+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":1052,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-12T17:36:47.608100+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":310,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-12T18:51:08.030316+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":86,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:36:11.858989+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":663,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-13T07:33:55.508962+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":1413,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:07:28.076287+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":300,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-12T17:58:36.524510+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":488,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:52:28.189043+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":512,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:49:21.633559+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":828,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-12T18:32:45.069248+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":443,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:44:45.168420+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":953,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:10:55.358674+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":717,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-13T06:07:15.116401+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":293,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:32:05.081505+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-13T06:40:53.697821+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":754,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:50:33.206753+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":269,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-12T17:42:17.524505+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":303,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-12T17:47:22.169064+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":494,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-13T06:47:07.418042+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":754,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-12T17:43:13.287273+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":387,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-12T18:44:32.763997+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":272,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-12T19:01:03.197425+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":271,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-push_T-random-s0-scene0.json"},{"created_at":"2026-10-12T18:03:36.179857+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:52:05.777935+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:08:15.768757+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":575,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-12T18:03:00.014662+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":492,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-13T06:12:46.532517+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":311,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:14:29.844674+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":531,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-12T18:42:23.934752+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":759,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-13T07:23:41.002935+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":835,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:52:36.450929+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:38:19.279830+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":442,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-12T18:50:30.620614+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-high-mixed42-20261013","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"high"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":878,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-high-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-high-mixed42-20261013-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-high-mixed42-20261013-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-12T12:18:49.885064+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:14:22.014865+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":533,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-12T16:47:11.545743+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":965,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:11:21.566275+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":511,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-12T11:23:36.813815+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":192,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-12T11:35:26.728180+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":367,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-12T12:13:38.441172+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":88,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:19:27.621336+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":718,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-12T17:04:50.094236+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1474,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-12T14:45:17.730898+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":776,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-12T15:55:26.970057+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":1058,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:37:04.170929+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":91,"model_responses":null,"native_controls":631,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:21:50.531562+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1100,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:22:14.517408+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":311,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:17:14.639436+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":788,"native_terminal":true,"score":0.75,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:25:29.421315+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":318,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-12T14:50:07.316092+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":698,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:34:42.719853+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":477,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-repair2-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-repair2-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-12T15:55:26.470272+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":61,"model_responses":null,"native_controls":346,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-retry1-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-retry1-push_T-random-s0-scene0.json"},{"created_at":"2026-10-12T16:19:26.039596+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":87,"model_responses":null,"native_controls":787,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-video3-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-video3-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-12T15:44:48.311196+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":625,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-init-video3-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-init-video3-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-12T11:23:01.331926+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":213,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-12T11:49:39.025357+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":493,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-12T14:45:41.251714+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":752,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-12T11:46:09.881900+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":332,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:05:21.530709+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":907,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-12T14:43:04.845700+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":256,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-12T14:42:52.196320+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":427,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:15:19.305672+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":610,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-12T11:44:54.639145+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":397,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-12T11:21:10.706974+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":223,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-12T15:58:03.163459+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":391,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-12T11:26:09.896390+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":337,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-12T12:08:40.257239+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":318,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-12T14:46:00.281987+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-12T14:49:15.857483+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":938,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-12T15:47:03.967342+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":386,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:40:12.583102+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":84,"model_responses":null,"native_controls":677,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:04:37.587257+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:12:20.273344+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":414,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-12T12:12:19.118222+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":854,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-mixed42-20261012-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-mixed42-20261012-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-14T05:09:13.286582+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":89,"model_responses":null,"native_controls":892,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-infra72retry1-20261014-organize_table-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-infra72retry1-20261014-organize_table-standard-s0-scene1.json"},{"created_at":"2026-10-13T08:25:03.685140+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-13T07:29:47.330206+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":520,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-13T10:00:22.926231+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":91,"model_responses":null,"native_controls":811,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-build_tower-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-build_tower-standard-s0-scene1.json"},{"created_at":"2026-10-13T10:14:48.166393+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1026,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-13T12:12:07.899239+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":1099,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-13T08:59:23.056542+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":532,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-13T07:34:02.195560+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":263,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-deposit_coin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-deposit_coin-standard-s0-scene1.json"},{"created_at":"2026-10-13T06:36:14.568007+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":376,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-13T07:36:37.853441+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":664,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-fill_egg_holder-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-fill_egg_holder-standard-s0-scene1.json"},{"created_at":"2026-10-13T09:26:30.885963+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1016,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-fill_pen_holder-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-fill_pen_holder-standard-s0-scene1.json"},{"created_at":"2026-10-13T06:30:03.859302+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":348,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-13T08:10:59.961942+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":9,"model_responses":9,"native_controls":73,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-13T08:40:57.619877+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":575,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-hang_mugs-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-hang_mugs-standard-s0-scene0.json"},{"created_at":"2026-10-13T13:58:45.850837+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":1458,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-13T07:49:02.062425+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":16,"model_responses":16,"native_controls":188,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-insert_key-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-insert_key-standard-s0-scene1.json"},{"created_at":"2026-10-13T07:28:35.808633+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":382,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-insert_tubes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-insert_tubes-standard-s0-scene1.json"},{"created_at":"2026-10-13T10:07:42.584621+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":461,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-make_kong-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-make_kong-standard-s0-scene1.json"},{"created_at":"2026-10-13T07:26:17.970194+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":606,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-make_toast-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-make_toast-standard-s0-scene0.json"},{"created_at":"2026-10-13T08:29:12.686389+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":450,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-13T06:11:23.876406+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":271,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-13T08:50:30.350284+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":410,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-13T10:15:18.832190+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":85,"model_responses":null,"native_controls":452,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-13T11:50:17.847207+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":759,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-play_stacking_toy-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-play_stacking_toy-standard-s0-scene1.json"},{"created_at":"2026-10-13T09:23:49.856349+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":442,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-play_tic_tac_toe-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-play_tic_tac_toe-standard-s0-scene1.json"},{"created_at":"2026-10-13T07:22:27.042422+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":312,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-13T06:48:10.954095+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":9,"model_responses":9,"native_controls":94,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-13T10:01:45.146737+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":786,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-pour_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-pour_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-13T06:34:25.070253+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-pour_liquid_into_cup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-pour_liquid_into_cup-standard-s0-scene0.json"},{"created_at":"2026-10-13T07:46:26.725892+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":169,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-13T09:17:25.841508+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":368,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-13T06:39:24.059065+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":537,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-13T08:41:14.104613+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":215,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-13T08:12:38.665226+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":538,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-13T07:14:16.133476+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":205,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-stack_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-stack_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-13T10:58:17.596333+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-13T06:42:38.157470+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":446,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-13T06:50:12.797376+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":713,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-store_laptop_and_headphones-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-store_laptop_and_headphones-standard-s0-scene0.json"},{"created_at":"2026-10-13T11:10:57.258377+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":815,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene1.json"},{"created_at":"2026-10-13T08:17:51.914904+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":394,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-13T08:50:41.342529+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":501,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-swap_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-swap_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-13T07:17:40.882771+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":740,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r2-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r2-mixed42-20261013-sweep_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r2-mixed42-20261013-sweep_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-14T05:08:18.795617+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":86,"model_responses":149,"native_controls":608,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-infra72retry1-20261014-fill_egg_holder-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-infra72retry1-20261014-fill_egg_holder-standard-s0-scene2.json"},{"created_at":"2026-10-14T06:32:30.304822+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":92,"model_responses":142,"native_controls":362,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-infra72retry1-20261014-make_kong-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-infra72retry1-20261014-make_kong-standard-s0-scene2.json"},{"created_at":"2026-10-14T06:27:30.297872+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":90,"model_responses":164,"native_controls":772,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-infra72retry1-20261014-organize_table-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-infra72retry1-20261014-organize_table-standard-s0-scene2.json"},{"created_at":"2026-10-14T05:26:39.629778+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":172,"native_controls":688,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-infra72retry1-20261014-play_tic_tac_toe-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-infra72retry1-20261014-play_tic_tac_toe-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:55:39.653381+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:18:02.698610+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":689,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-13T10:56:33.907094+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1050,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-build_tower-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-build_tower-standard-s0-scene2.json"},{"created_at":"2026-10-13T12:00:09.569813+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":1096,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-13T16:22:24.119328+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":971,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-13T15:12:22.737038+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":632,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:07:49.130125+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":296,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-deposit_coin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-deposit_coin-standard-s0-scene2.json"},{"created_at":"2026-10-13T11:16:39.032408+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":966,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-13T11:55:29.699150+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1067,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-fill_pen_holder-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-fill_pen_holder-standard-s0-scene2.json"},{"created_at":"2026-10-13T09:29:26.493778+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":315,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-13T14:32:20.604313+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":134,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-13T11:14:54.687558+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":603,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-hang_mugs-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-hang_mugs-random-s0-scene1.json"},{"created_at":"2026-10-13T16:55:05.488493+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1478,"native_terminal":true,"score":0.05,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:08:15.237163+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":237,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-insert_key-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-insert_key-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:26:19.010121+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-insert_tubes-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-insert_tubes-standard-s0-scene2.json"},{"created_at":"2026-10-13T11:20:32.732038+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":412,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-make_toast-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-make_toast-random-s0-scene1.json"},{"created_at":"2026-10-13T14:32:41.252467+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":556,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-13T11:23:51.839411+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":786,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-13T15:18:32.269493+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":476,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:26:41.278515+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":366,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-13T15:47:20.108925+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":601,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-play_stacking_toy-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-play_stacking_toy-standard-s0-scene2.json"},{"created_at":"2026-10-13T11:25:01.784675+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":334,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:15:34.002389+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":587,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-13T15:47:50.922010+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":768,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-pour_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-pour_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-13T11:02:02.762705+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":379,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-pour_liquid_into_cup-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-pour_liquid_into_cup-random-s0-scene1.json"},{"created_at":"2026-10-13T14:50:33.162213+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:16:18.704839+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":403,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-push_T-random-s0-scene1.json"},{"created_at":"2026-10-13T08:51:53.490752+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":649,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:54:25.330985+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-13T15:20:01.637044+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":811,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-13T08:40:09.543560+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":354,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-stack_blocks-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-stack_blocks-random-s0-scene1.json"},{"created_at":"2026-10-13T15:22:50.162662+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-13T11:26:56.861014+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":84,"model_responses":null,"native_controls":776,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-13T14:04:16.773463+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":69,"model_responses":null,"native_controls":765,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-store_laptop_and_headphones-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-store_laptop_and_headphones-random-s0-scene1.json"},{"created_at":"2026-10-13T16:36:59.432714+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":801,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene2.json"},{"created_at":"2026-10-13T15:06:51.797036+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:30:37.910779+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":423,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-swap_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-swap_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-13T14:53:29.819774+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":771,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r3-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r3-mixed42-20261013-sweep_blocks-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r3-mixed42-20261013-sweep_blocks-random-s0-scene1.json"},{"created_at":"2026-10-14T07:41:54.626698+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":89,"model_responses":null,"native_controls":700,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-infra72retry1-20261014-build_tower-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-infra72retry1-20261014-build_tower-standard-s0-scene3.json"},{"created_at":"2026-10-14T08:31:40.506391+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":89,"model_responses":null,"native_controls":1014,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-infra72retry1-20261014-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-infra72retry1-20261014-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-14T07:36:32.431283+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":87,"model_responses":null,"native_controls":859,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-infra72retry1-20261014-fill_pen_holder-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-infra72retry1-20261014-fill_pen_holder-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:11:37.237381+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":166,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:25:09.907460+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":624,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-13T18:10:53.329697+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":1100,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:17:22.688989+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":548,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:24:26.259516+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":288,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-deposit_coin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-deposit_coin-standard-s0-scene3.json"},{"created_at":"2026-10-13T15:25:05.691001+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":946,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:42:43.632873+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":676,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-fill_egg_holder-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-fill_egg_holder-standard-s0-scene3.json"},{"created_at":"2026-10-13T15:35:09.751826+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":326,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-13T17:20:43.963170+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":192,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:32:36.901296+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":538,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-hang_mugs-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-hang_mugs-standard-s0-scene1.json"},{"created_at":"2026-10-13T18:21:11.845245+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":1357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:30:43.021338+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":245,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-insert_key-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-insert_key-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:56:11.425626+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-insert_tubes-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-insert_tubes-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:20:08.201892+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":427,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-make_kong-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-make_kong-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:21:59.316785+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":775,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-make_toast-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-make_toast-standard-s0-scene1.json"},{"created_at":"2026-10-13T16:52:47.896243+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":311,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-13T15:46:10.760217+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":759,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-organize_table-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-organize_table-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:58:56.341112+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":991,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-13T17:22:26.465095+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":207,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:09:23.056339+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":447,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:38:58.254976+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":522,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-play_stacking_toy-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-play_stacking_toy-standard-s0-scene3.json"},{"created_at":"2026-10-13T15:50:16.888396+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":261,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-play_tic_tac_toe-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-play_tic_tac_toe-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:39:54.942336+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":340,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:52:34.365928+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":464,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:57:05.333478+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":705,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-pour_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-pour_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-13T15:49:34.994252+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-pour_liquid_into_cup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-pour_liquid_into_cup-standard-s0-scene1.json"},{"created_at":"2026-10-13T17:19:25.275047+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":364,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:01:18.810094+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":543,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-13T14:23:01.975686+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":669,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:21:12.660110+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":260,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:18:30.923695+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":533,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-13T11:28:22.723243+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":194,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-stack_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-stack_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-13T17:24:29.345183+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":384,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-13T15:48:10.183434+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":523,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-13T11:24:26.592582+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":552,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-store_laptop_and_headphones-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-store_laptop_and_headphones-standard-s0-scene1.json"},{"created_at":"2026-10-13T18:07:19.302063+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":878,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:00:37.453863+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-13T17:11:04.181142+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":436,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-swap_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-swap_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-13T16:24:30.508004+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":613,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r4-mixed42-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r4-mixed42-20261013-sweep_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r4-mixed42-20261013-sweep_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-14T20:30:04.976407+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":145,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-align_blocks-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-align_blocks-standard-s0-scene4.json"},{"created_at":"2026-10-14T19:14:10.143655+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":63,"model_responses":null,"native_controls":464,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-arrange_largest_number-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-arrange_largest_number-random-s0-scene2.json"},{"created_at":"2026-10-14T19:37:28.055157+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":782,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-build_tower-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-build_tower-standard-s0-scene4.json"},{"created_at":"2026-10-14T19:28:04.195578+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1042,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-classify_objects-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-classify_objects-standard-s0-scene4.json"},{"created_at":"2026-10-14T21:58:45.702683+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":1028,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-classify_objects_by_language-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-classify_objects_by_language-standard-s0-scene4.json"},{"created_at":"2026-10-14T19:26:08.481120+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":500,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-cover_blocks-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-cover_blocks-standard-s0-scene4.json"},{"created_at":"2026-10-14T16:13:41.383168+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":257,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-deposit_coin-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-deposit_coin-standard-s0-scene4.json"},{"created_at":"2026-10-14T19:21:08.529065+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":80,"model_responses":null,"native_controls":486,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-fasten_screws-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-fasten_screws-standard-s0-scene4.json"},{"created_at":"2026-10-14T19:48:47.629358+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":700,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-fill_egg_holder-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-fill_egg_holder-standard-s0-scene4.json"},{"created_at":"2026-10-14T19:29:22.126689+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1036,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-fill_pen_holder-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-fill_pen_holder-standard-s0-scene4.json"},{"created_at":"2026-10-14T14:44:01.809988+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":344,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-fold_clothes-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-fold_clothes-random-s0-scene2.json"},{"created_at":"2026-10-14T20:31:40.229894+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":195,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-general_pickup-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-general_pickup-standard-s0-scene4.json"},{"created_at":"2026-10-14T15:34:20.794658+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":474,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-hang_mugs-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-hang_mugs-random-s0-scene2.json"},{"created_at":"2026-10-15T05:59:19.488077+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":752,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014-initretry1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-initretry1-pour_by_language-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-initretry1-pour_by_language-standard-s0-scene4.json"},{"created_at":"2026-10-14T17:28:44.624070+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":28,"model_responses":null,"native_controls":245,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-insert_key-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-insert_key-standard-s0-scene4.json"},{"created_at":"2026-10-14T18:35:49.998648+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":44,"model_responses":null,"native_controls":355,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-insert_tubes-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-insert_tubes-standard-s0-scene4.json"},{"created_at":"2026-10-14T19:44:44.877208+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":493,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-make_kong-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-make_kong-standard-s0-scene4.json"},{"created_at":"2026-10-14T18:01:42.406818+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":57,"model_responses":null,"native_controls":395,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-make_toast-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-make_toast-random-s0-scene2.json"},{"created_at":"2026-10-14T21:02:54.734429+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":356,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-match_and_pick_from_conveyor-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-match_and_pick_from_conveyor-standard-s0-scene4.json"},{"created_at":"2026-10-14T19:44:51.343294+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":759,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-organize_table-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-organize_table-standard-s0-scene4.json"},{"created_at":"2026-10-14T15:19:49.470606+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":807,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-pack_objects_into_box-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-pack_objects_into_box-random-s0-scene2.json"},{"created_at":"2026-10-14T20:31:42.069479+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":276,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-pick_from_conveyor_by_image-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-pick_from_conveyor_by_image-standard-s0-scene4.json"},{"created_at":"2026-10-14T20:25:38.230374+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-play_Xylophone-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-play_Xylophone-standard-s0-scene4.json"},{"created_at":"2026-10-14T22:10:41.437922+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":586,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-play_stacking_toy-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-play_stacking_toy-standard-s0-scene4.json"},{"created_at":"2026-10-14T20:53:39.932226+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":238,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-play_tic_tac_toe-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-play_tic_tac_toe-standard-s0-scene4.json"},{"created_at":"2026-10-14T16:48:30.170738+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":395,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-plug_in_charger-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-plug_in_charger-standard-s0-scene4.json"},{"created_at":"2026-10-14T17:34:19.456622+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":29,"model_responses":null,"native_controls":262,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-pour_balls_into_vase-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-pour_balls_into_vase-standard-s0-scene4.json"},{"created_at":"2026-10-14T15:43:51.064732+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":158,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-pour_liquid_into_cup-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-pour_liquid_into_cup-random-s0-scene2.json"},{"created_at":"2026-10-14T20:45:54.191005+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":270,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-press_by_number-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-press_by_number-standard-s0-scene4.json"},{"created_at":"2026-10-14T13:17:13.405689+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":191,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-push_T-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-push_T-random-s0-scene2.json"},{"created_at":"2026-10-14T18:57:43.037980+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-put_bottles_into_dustbin-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-put_bottles_into_dustbin-standard-s0-scene4.json"},{"created_at":"2026-10-14T20:55:40.496579+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-solve_equation-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-solve_equation-standard-s0-scene4.json"},{"created_at":"2026-10-14T16:27:22.483272+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":518,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-sort_nesting_dolls_by_size-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-sort_nesting_dolls_by_size-random-s0-scene2.json"},{"created_at":"2026-10-14T19:11:01.972922+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":329,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-stack_blocks-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-stack_blocks-random-s0-scene2.json"},{"created_at":"2026-10-14T21:05:24.398156+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":340,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-stack_blocks_by_language-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-stack_blocks_by_language-standard-s0-scene4.json"},{"created_at":"2026-10-14T14:12:18.377437+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":745,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-stack_bowls-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-stack_bowls-random-s0-scene2.json"},{"created_at":"2026-10-14T16:15:52.929075+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":254,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-store_laptop_and_headphones-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-store_laptop_and_headphones-random-s0-scene2.json"},{"created_at":"2026-10-14T21:31:16.158109+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":755,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-store_tools_in_toolbox-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-store_tools_in_toolbox-standard-s0-scene4.json"},{"created_at":"2026-10-14T20:51:24.588067+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-swap_T-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-swap_T-standard-s0-scene4.json"},{"created_at":"2026-10-14T20:47:33.034615+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":440,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-swap_blocks-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-swap_blocks-standard-s0-scene4.json"},{"created_at":"2026-10-14T16:17:32.919047+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":438,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-mixed42-20261014-sweep_blocks-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-mixed42-20261014-sweep_blocks-random-s0-scene2.json"},{"created_at":"2026-10-15T19:24:46.741208+00:00","episode":{"capability":"Memory","scene":55,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1391,"native_terminal":true,"score":0.05,"status":"complete","success":false},"protocol":{"id":"l3-low-r5-scene55-substitute-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r5-scene55-substitute-20261015-imitate_sorting_sequence-standard-s0-scene55","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r5-scene55-substitute-20261015-imitate_sorting_sequence-standard-s0-scene55.json"},{"created_at":"2026-10-14T22:06:21.980311+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":168,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-align_blocks-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-align_blocks-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:17:36.693709+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":776,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-arrange_largest_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-arrange_largest_number-standard-s0-scene2.json"},{"created_at":"2026-10-14T22:20:29.400853+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":864,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-build_tower-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-build_tower-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:35:29.079109+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":638,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-classify_objects-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-classify_objects-standard-s0-scene5.json"},{"created_at":"2026-10-14T23:13:05.804855+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":972,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-classify_objects_by_language-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-classify_objects_by_language-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:19:02.677519+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":499,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-cover_blocks-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-cover_blocks-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:06:24.499508+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":300,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-deposit_coin-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-deposit_coin-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:22:53.688305+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":403,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-fasten_screws-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-fasten_screws-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:11:24.323710+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":495,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-fill_egg_holder-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-fill_egg_holder-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:25:08.755415+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1001,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-fill_pen_holder-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-fill_pen_holder-standard-s0-scene5.json"},{"created_at":"2026-10-14T20:45:45.899245+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":426,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-fold_clothes-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-fold_clothes-standard-s0-scene2.json"},{"created_at":"2026-10-14T21:56:11.398288+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":109,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-general_pickup-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-general_pickup-standard-s0-scene5.json"},{"created_at":"2026-10-14T20:54:04.630153+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":392,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-hang_mugs-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-hang_mugs-standard-s0-scene2.json"},{"created_at":"2026-10-14T23:29:14.869662+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1462,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-imitate_sorting_sequence-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-imitate_sorting_sequence-standard-s0-scene5.json"},{"created_at":"2026-10-15T04:30:54.969528+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":281,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014-initretry1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-initretry1-plug_in_charger-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-initretry1-plug_in_charger-standard-s0-scene5.json"},{"created_at":"2026-10-15T05:00:39.404119+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014-initretry1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-initretry1-pour_by_language-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-initretry1-pour_by_language-standard-s0-scene5.json"},{"created_at":"2026-10-15T04:17:18.279512+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":10,"model_responses":10,"native_controls":125,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014-initretry1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-initretry1-pour_liquid_into_cup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-initretry1-pour_liquid_into_cup-standard-s0-scene2.json"},{"created_at":"2026-10-14T21:05:16.474790+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":220,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-insert_key-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-insert_key-standard-s0-scene5.json"},{"created_at":"2026-10-14T20:57:42.346920+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":138,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-insert_tubes-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-insert_tubes-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:41:04.303885+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":522,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-make_kong-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-make_kong-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:46:33.638160+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":610,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-make_toast-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-make_toast-standard-s0-scene2.json"},{"created_at":"2026-10-14T22:16:50.762491+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":536,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-match_and_pick_from_conveyor-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-match_and_pick_from_conveyor-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:27:19.668124+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":728,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-organize_table-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-organize_table-standard-s0-scene5.json"},{"created_at":"2026-10-14T20:45:20.346118+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":458,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-pack_objects_into_box-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-pack_objects_into_box-standard-s0-scene2.json"},{"created_at":"2026-10-14T22:15:02.424998+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":211,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-pick_from_conveyor_by_image-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-pick_from_conveyor_by_image-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:45:53.382364+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":296,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-play_Xylophone-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-play_Xylophone-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:41:25.742995+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":538,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-play_stacking_toy-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-play_stacking_toy-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:40:41.452307+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":257,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-play_tic_tac_toe-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-play_tic_tac_toe-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:11:01.076147+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":447,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-pour_balls_into_vase-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-pour_balls_into_vase-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:59:50.741322+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":295,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-press_by_number-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-press_by_number-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:31:26.734396+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":591,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-push_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-push_T-standard-s0-scene2.json"},{"created_at":"2026-10-14T21:55:40.729232+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-put_bottles_into_dustbin-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-put_bottles_into_dustbin-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:23:19.435688+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":275,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-solve_equation-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-solve_equation-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:15:46.401966+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":860,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-sort_nesting_dolls_by_size-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-sort_nesting_dolls_by_size-standard-s0-scene2.json"},{"created_at":"2026-10-14T21:20:28.323086+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":392,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-stack_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-stack_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-14T22:35:53.979308+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":393,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-stack_blocks_by_language-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-stack_blocks_by_language-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:19:11.217669+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":740,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-stack_bowls-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-stack_bowls-standard-s0-scene2.json"},{"created_at":"2026-10-14T21:43:33.594427+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":602,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-store_laptop_and_headphones-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-store_laptop_and_headphones-standard-s0-scene2.json"},{"created_at":"2026-10-14T22:52:59.676805+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":570,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-store_tools_in_toolbox-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-store_tools_in_toolbox-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:57:12.871209+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":284,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-swap_T-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-swap_T-standard-s0-scene5.json"},{"created_at":"2026-10-14T22:16:18.866810+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":415,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-swap_blocks-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-swap_blocks-standard-s0-scene5.json"},{"created_at":"2026-10-14T21:37:45.299807+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":837,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r6-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r6-mixed42-20261014-sweep_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r6-mixed42-20261014-sweep_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-14T23:47:49.371273+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":188,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-align_blocks-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-align_blocks-standard-s0-scene6.json"},{"created_at":"2026-10-15T00:08:51.766891+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":745,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-arrange_largest_number-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-arrange_largest_number-random-s0-scene3.json"},{"created_at":"2026-10-15T00:04:20.680997+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":806,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-build_tower-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-build_tower-standard-s0-scene6.json"},{"created_at":"2026-10-15T00:13:20.547476+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":960,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-classify_objects-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-classify_objects-standard-s0-scene6.json"},{"created_at":"2026-10-15T00:24:09.357931+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":834,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-classify_objects_by_language-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-classify_objects_by_language-standard-s0-scene6.json"},{"created_at":"2026-10-15T00:08:47.418159+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":641,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-cover_blocks-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-cover_blocks-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:00:21.518535+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":274,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-deposit_coin-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-deposit_coin-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:49:47.095917+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":981,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-fasten_screws-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-fasten_screws-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:18:51.677938+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":350,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-fill_egg_holder-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-fill_egg_holder-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:42:04.352754+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":671,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-fill_pen_holder-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-fill_pen_holder-standard-s0-scene6.json"},{"created_at":"2026-10-14T22:30:32.708008+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":297,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-fold_clothes-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-fold_clothes-random-s0-scene3.json"},{"created_at":"2026-10-14T23:37:31.789275+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":112,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-general_pickup-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-general_pickup-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:13:13.157255+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":669,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-hang_mugs-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-hang_mugs-random-s0-scene3.json"},{"created_at":"2026-10-15T00:49:47.650373+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":1375,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-imitate_sorting_sequence-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-imitate_sorting_sequence-standard-s0-scene6.json"},{"created_at":"2026-10-15T05:09:01.770686+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":727,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014-initretry1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-initretry1-pour_by_language-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-initretry1-pour_by_language-standard-s0-scene6.json"},{"created_at":"2026-10-15T04:32:54.828181+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":314,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014-initretry1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-initretry1-pour_liquid_into_cup-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-initretry1-pour_liquid_into_cup-random-s0-scene3.json"},{"created_at":"2026-10-14T22:56:44.144734+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":257,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-insert_key-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-insert_key-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:06:04.604109+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":484,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-insert_tubes-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-insert_tubes-standard-s0-scene6.json"},{"created_at":"2026-10-15T00:28:04.791535+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":385,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-make_kong-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-make_kong-standard-s0-scene6.json"},{"created_at":"2026-10-14T22:44:37.527582+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":292,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-make_toast-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-make_toast-random-s0-scene3.json"},{"created_at":"2026-10-14T23:27:21.610254+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":372,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-match_and_pick_from_conveyor-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-match_and_pick_from_conveyor-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:58:56.949076+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":636,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-organize_table-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-organize_table-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:01:12.327462+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":583,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-pack_objects_into_box-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-pack_objects_into_box-random-s0-scene3.json"},{"created_at":"2026-10-14T23:56:52.132260+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":243,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-pick_from_conveyor_by_image-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-pick_from_conveyor_by_image-standard-s0-scene6.json"},{"created_at":"2026-10-15T00:02:42.599602+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-play_Xylophone-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-play_Xylophone-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:55:39.042137+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":436,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-play_stacking_toy-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-play_stacking_toy-standard-s0-scene6.json"},{"created_at":"2026-10-15T00:22:52.182547+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":260,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-play_tic_tac_toe-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-play_tic_tac_toe-standard-s0-scene6.json"},{"created_at":"2026-10-14T22:57:03.162536+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":382,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-plug_in_charger-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-plug_in_charger-standard-s0-scene6.json"},{"created_at":"2026-10-14T22:44:32.290560+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":6,"model_responses":6,"native_controls":83,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-pour_balls_into_vase-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-pour_balls_into_vase-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:27:40.866633+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":259,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-press_by_number-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-press_by_number-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:44:58.455610+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":482,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-push_T-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-push_T-random-s0-scene3.json"},{"created_at":"2026-10-14T23:21:15.733336+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-put_bottles_into_dustbin-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-put_bottles_into_dustbin-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:58:09.775576+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-solve_equation-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-solve_equation-standard-s0-scene6.json"},{"created_at":"2026-10-14T22:39:49.060050+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":237,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-sort_nesting_dolls_by_size-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-sort_nesting_dolls_by_size-random-s0-scene3.json"},{"created_at":"2026-10-14T22:56:26.228983+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":403,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-stack_blocks-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-stack_blocks-random-s0-scene3.json"},{"created_at":"2026-10-15T00:01:40.648872+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":395,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-stack_blocks_by_language-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-stack_blocks_by_language-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:09:51.966589+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":568,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-stack_bowls-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-stack_bowls-random-s0-scene3.json"},{"created_at":"2026-10-14T23:07:39.633761+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":634,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-store_laptop_and_headphones-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-store_laptop_and_headphones-random-s0-scene3.json"},{"created_at":"2026-10-15T00:57:38.142684+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":705,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-store_tools_in_toolbox-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-store_tools_in_toolbox-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:36:49.916959+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":383,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-swap_T-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-swap_T-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:50:21.825249+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":507,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-swap_blocks-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-swap_blocks-standard-s0-scene6.json"},{"created_at":"2026-10-14T23:09:35.218293+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":524,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r7-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r7-mixed42-20261014-sweep_blocks-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r7-mixed42-20261014-sweep_blocks-random-s0-scene3.json"},{"created_at":"2026-10-15T01:23:56.033236+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":148,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-align_blocks-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-align_blocks-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:13:52.451185+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":339,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-arrange_largest_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-arrange_largest_number-standard-s0-scene3.json"},{"created_at":"2026-10-15T01:46:47.566633+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":900,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-build_tower-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-build_tower-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:00:36.258435+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":771,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-classify_objects-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-classify_objects-standard-s0-scene7.json"},{"created_at":"2026-10-15T02:17:09.405498+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":895,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-classify_objects_by_language-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-classify_objects_by_language-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:31:06.629457+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":649,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-cover_blocks-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-cover_blocks-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:24:41.600927+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":239,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-deposit_coin-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-deposit_coin-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:35:59.740582+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1142,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-fasten_screws-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-fasten_screws-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:25:26.864641+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":481,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-fill_egg_holder-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-fill_egg_holder-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:47:03.988999+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":567,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-fill_pen_holder-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-fill_pen_holder-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:04:41.182731+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":102,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-general_pickup-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-general_pickup-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:14:14.324338+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":338,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-hang_mugs-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-hang_mugs-standard-s0-scene3.json"},{"created_at":"2026-10-15T02:37:47.872163+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":1315,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-imitate_sorting_sequence-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-imitate_sorting_sequence-standard-s0-scene7.json"},{"created_at":"2026-10-15T04:38:16.267620+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":398,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014-initretry1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-initretry1-fold_clothes-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-initretry1-fold_clothes-standard-s0-scene3.json"},{"created_at":"2026-10-15T00:25:41.190264+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":240,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-insert_key-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-insert_key-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:44:14.844911+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-insert_tubes-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-insert_tubes-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:37:48.736445+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":312,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-make_kong-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-make_kong-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:05:41.572778+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":704,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-make_toast-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-make_toast-standard-s0-scene3.json"},{"created_at":"2026-10-15T00:56:23.297145+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-match_and_pick_from_conveyor-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-match_and_pick_from_conveyor-standard-s0-scene7.json"},{"created_at":"2026-10-15T02:04:51.452569+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":675,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-organize_table-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-organize_table-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:17:35.449085+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":482,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-pack_objects_into_box-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-pack_objects_into_box-standard-s0-scene3.json"},{"created_at":"2026-10-15T01:34:09.234707+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":441,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-pick_from_conveyor_by_image-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-pick_from_conveyor_by_image-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:29:48.736534+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-play_Xylophone-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-play_Xylophone-standard-s0-scene7.json"},{"created_at":"2026-10-15T02:14:46.681119+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":568,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-play_stacking_toy-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-play_stacking_toy-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:57:52.978011+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":254,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-play_tic_tac_toe-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-play_tic_tac_toe-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:31:49.427356+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":398,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-plug_in_charger-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-plug_in_charger-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:31:58.755769+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":337,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-pour_balls_into_vase-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-pour_balls_into_vase-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:40:54.670352+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":627,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-pour_by_language-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-pour_by_language-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:05:38.744162+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":230,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-pour_liquid_into_cup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-pour_liquid_into_cup-standard-s0-scene3.json"},{"created_at":"2026-10-15T01:09:08.184515+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":352,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-press_by_number-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-press_by_number-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:07:23.620372+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":298,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-push_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-push_T-standard-s0-scene3.json"},{"created_at":"2026-10-15T01:06:40.275781+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-put_bottles_into_dustbin-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-put_bottles_into_dustbin-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:20:47.986017+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-solve_equation-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-solve_equation-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:28:41.674368+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":889,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-sort_nesting_dolls_by_size-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-sort_nesting_dolls_by_size-standard-s0-scene3.json"},{"created_at":"2026-10-15T00:25:53.396086+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":292,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-stack_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-stack_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-15T01:33:47.628689+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":391,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-stack_blocks_by_language-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-stack_blocks_by_language-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:14:12.631239+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":383,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-stack_bowls-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-stack_bowls-standard-s0-scene3.json"},{"created_at":"2026-10-15T00:58:55.063394+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":754,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-store_laptop_and_headphones-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-store_laptop_and_headphones-standard-s0-scene3.json"},{"created_at":"2026-10-15T02:10:47.462536+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":654,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-store_tools_in_toolbox-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-store_tools_in_toolbox-standard-s0-scene7.json"},{"created_at":"2026-10-15T00:55:26.310621+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":341,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-swap_T-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-swap_T-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:10:20.519012+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":415,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-swap_blocks-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-swap_blocks-standard-s0-scene7.json"},{"created_at":"2026-10-15T01:02:20.420293+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":521,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-low-r8-mixed42-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-low-r8-mixed42-20261014-sweep_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-low-r8-mixed42-20261014-sweep_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-16T07:13:27.389421+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":17,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:40:14.111353+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":56,"native_controls":452,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-16T00:27:04.085783+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":126,"native_controls":599,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-16T01:27:03.781280+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":116,"native_controls":732,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-16T07:51:41.299049+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":192,"native_controls":646,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T03:30:26.499067+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":8,"model_responses":10,"native_controls":104,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-15T23:54:51.602572+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":37,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-15T22:46:11.759644+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":120,"native_controls":1079,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-16T02:16:45.029396+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":114,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-16T01:03:22.590439+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":89,"native_controls":556,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-15T19:21:08.216723+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":136,"native_controls":482,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-16T08:24:18.171231+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-15T19:38:34.288773+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":59,"native_controls":454,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-16T00:03:35.995716+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":28,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-15T23:10:27.009469+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":61,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-16T02:54:15.876810+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":459,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:24:35.533823+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":32,"native_controls":378,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-16T03:41:50.011874+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":47,"native_controls":567,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-16T02:32:40.907130+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":66,"native_controls":554,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-15T18:53:28.161346+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":95,"native_controls":674,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-15T23:45:33.940233+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":128,"native_controls":496,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-16T03:24:32.742000+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":166,"native_controls":1186,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-16T01:56:28.744828+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":165,"native_controls":808,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-15T22:57:37.014813+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":46,"native_controls":386,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-15T23:22:12.647462+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":50,"native_controls":506,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:13:36.324882+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":36,"native_controls":233,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-16T07:06:36.802652+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":79,"native_controls":598,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-15T18:33:58.736711+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":47,"native_controls":481,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-push_T-random-s0-scene0.json"},{"created_at":"2026-10-16T00:46:40.225936+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":76,"native_controls":671,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-16T10:31:59.754881+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":114,"native_controls":1394,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-rerun1650-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-rerun1650-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-16T09:24:54.467612+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":66,"native_controls":461,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-rerun1650-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-rerun1650-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-16T09:32:00.447651+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":82,"native_controls":447,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-rerun1650-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-rerun1650-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T08:33:39.476668+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":32,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:56:50.168771+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":66,"native_controls":423,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-15T21:33:06.445466+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":65,"native_controls":523,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-16T07:23:55.542500+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":69,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-15T21:17:49.073593+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":92,"native_controls":621,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-16T08:40:29.097918+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":82,"native_controls":459,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-16T10:06:24.147052+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":53,"native_controls":460,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-supplement84-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-supplement84-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T06:38:29.054064+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":37,"native_controls":317,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:01:37.137554+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-cap20-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":108,"native_controls":858,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-cap20-medium-r1-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-luna-cap20-medium-r1-20261016-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-cap20-medium-r1-20261016-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-16T06:37:51.460629+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":19,"model_responses":20,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:59:50.339037+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":26,"native_controls":382,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-15T23:39:50.689445+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":80,"native_controls":872,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-16T00:26:19.440454+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":124,"native_controls":742,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-16T07:01:25.302859+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":51,"native_controls":509,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T02:07:30.124358+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":9,"model_responses":11,"native_controls":160,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-15T23:16:24.772526+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":35,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-15T22:06:15.927946+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":87,"native_controls":596,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-16T01:09:42.739890+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":71,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-16T00:00:19.623719+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":25,"native_controls":244,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-15T19:27:58.141803+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":94,"native_controls":293,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-16T06:45:25.543172+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":42,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-15T19:57:41.284918+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":142,"native_controls":796,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-15T23:23:07.220460+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":19,"model_responses":23,"native_controls":291,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-15T22:41:17.656225+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":62,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-16T01:37:55.200511+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":537,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:49:19.399599+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":45,"native_controls":637,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-16T02:24:17.369909+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":81,"native_controls":618,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-16T01:21:21.708677+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":44,"native_controls":623,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-15T19:10:29.300465+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":112,"native_controls":934,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-16T07:37:26.722010+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":117,"native_controls":544,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-15T23:07:19.253424+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":71,"native_controls":279,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-16T02:01:58.537131+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":136,"native_controls":1200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-16T00:53:01.375403+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":105,"native_controls":893,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-15T22:20:26.973815+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":44,"native_controls":345,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-15T22:51:51.541193+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":34,"native_controls":581,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-16T08:27:24.228660+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":24,"native_controls":358,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:27:40.120788+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":29,"native_controls":375,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-16T03:34:35.927858+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":387,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-15T18:48:59.591861+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":37,"native_controls":512,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-push_T-random-s0-scene0.json"},{"created_at":"2026-10-15T23:52:24.161879+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":51,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-16T07:10:02.947445+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":142,"native_controls":251,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-15T21:10:10.502245+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":25,"native_controls":740,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-15T21:43:36.768544+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":56,"native_controls":550,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-16T06:47:28.814695+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":38,"native_controls":386,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-15T18:36:42.409511+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":66,"native_controls":754,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-15T21:26:50.609380+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":65,"native_controls":763,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-16T07:16:40.345933+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":63,"native_controls":864,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-16T10:24:19.233393+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":103,"native_controls":1342,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-supplement84-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-supplement84-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-16T02:58:42.162483+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":47,"native_controls":362,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-16T02:46:17.094821+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":112,"native_controls":656,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-15T20:16:39.872674+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-luna-nocap-medium-r1-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":76,"native_controls":681,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-luna-nocap-medium-r1-20261016","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"l3-luna-nocap-medium-r1-20261016-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-luna-nocap-medium-r1-20261016-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-18T10:25:27.121346+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":621,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt2-20261018-arrange_largest_number-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt2-20261018-arrange_largest_number-random-s0-scene2.json"},{"created_at":"2026-10-18T10:20:33.312770+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":706,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt2-20261018-hang_mugs-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt2-20261018-hang_mugs-random-s0-scene2.json"},{"created_at":"2026-10-18T10:19:13.450732+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":555,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt2-20261018-make_toast-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt2-20261018-make_toast-random-s0-scene2.json"},{"created_at":"2026-10-18T10:21:30.287568+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1048,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt2-20261018-pack_objects_into_box-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt2-20261018-pack_objects_into_box-random-s0-scene2.json"},{"created_at":"2026-10-18T10:01:26.432433+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt2-20261018-pour_liquid_into_cup-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt2-20261018-pour_liquid_into_cup-random-s0-scene2.json"},{"created_at":"2026-10-18T10:22:26.864116+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":753,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt2-20261018-store_laptop_and_headphones-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt2-20261018-store_laptop_and_headphones-random-s0-scene2.json"},{"created_at":"2026-10-18T10:15:21.865765+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":894,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt2-20261018-sweep_blocks-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt2-20261018-sweep_blocks-random-s0-scene2.json"},{"created_at":"2026-10-18T10:53:41.997134+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":461,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt3-20261018-fold_clothes-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt3-20261018-fold_clothes-random-s0-scene2.json"},{"created_at":"2026-10-18T11:05:03.055592+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":379,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt3-20261018-push_T-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt3-20261018-push_T-random-s0-scene2.json"},{"created_at":"2026-10-18T11:05:31.199976+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":735,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt3-20261018-stack_bowls-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt3-20261018-stack_bowls-random-s0-scene2.json"},{"created_at":"2026-10-18T12:13:18.047661+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":989,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt4-20261018-sort_nesting_dolls_by_size-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt4-20261018-sort_nesting_dolls_by_size-random-s0-scene2.json"},{"created_at":"2026-10-18T11:57:09.421900+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":365,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r5-random-scene2-20261018","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-random-scene2-attempt4-20261018-stack_blocks-random-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-random-scene2-attempt4-20261018-stack_blocks-random-s0-scene2.json"},{"created_at":"2026-10-17T10:51:30.324654+00:00","episode":{"capability":"Memory","scene":55,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1600,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r5-scene55-substitute-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r5-scene55-substitute-20261017-imitate_sorting_sequence-standard-s0-scene55","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r5-scene55-substitute-20261017-imitate_sorting_sequence-standard-s0-scene55.json"},{"created_at":"2026-10-15T21:01:35.262144+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":164,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-align_blocks-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-align_blocks-standard-s0-scene6.json"},{"created_at":"2026-10-15T21:24:10.176096+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":798,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-arrange_largest_number-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-arrange_largest_number-random-s0-scene3.json"},{"created_at":"2026-10-15T20:56:41.132375+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":814,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-build_tower-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-build_tower-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:31:01.655543+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":744,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-classify_objects-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-classify_objects-standard-s0-scene6.json"},{"created_at":"2026-10-16T04:17:15.789846+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":943,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-classify_objects_by_language-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-classify_objects_by_language-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:59:01.071170+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":481,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-cover_blocks-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-cover_blocks-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:37:25.119980+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":278,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-deposit_coin-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-deposit_coin-standard-s0-scene6.json"},{"created_at":"2026-10-16T04:34:33.036394+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1296,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-fasten_screws-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-fasten_screws-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:49:02.909086+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":667,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-fill_egg_holder-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-fill_egg_holder-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:58:32.941789+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":866,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-fill_pen_holder-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-fill_pen_holder-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:30:25.215062+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":472,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-fold_clothes-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-fold_clothes-random-s0-scene3.json"},{"created_at":"2026-10-15T21:04:18.967599+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":121,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-general_pickup-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-general_pickup-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:41:15.989139+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":567,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-hang_mugs-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-hang_mugs-random-s0-scene3.json"},{"created_at":"2026-10-16T04:46:51.764392+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1518,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:13:55.510013+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":296,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-insert_key-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-insert_key-standard-s0-scene6.json"},{"created_at":"2026-10-15T21:21:47.939716+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":500,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-insert_tubes-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-insert_tubes-standard-s0-scene6.json"},{"created_at":"2026-10-16T04:26:18.241774+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":539,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-make_kong-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-make_kong-standard-s0-scene6.json"},{"created_at":"2026-10-16T04:27:51.004125+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":649,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-make_toast-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-make_toast-random-s0-scene3.json"},{"created_at":"2026-10-15T20:50:13.824797+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":438,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene6.json"},{"created_at":"2026-10-16T04:04:31.480588+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":864,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-organize_table-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-organize_table-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:58:08.418797+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":838,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-pack_objects_into_box-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-pack_objects_into_box-random-s0-scene3.json"},{"created_at":"2026-10-15T21:22:07.481384+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":529,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene6.json"},{"created_at":"2026-10-16T04:03:14.992904+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":375,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-play_Xylophone-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-play_Xylophone-standard-s0-scene6.json"},{"created_at":"2026-10-16T03:41:00.075713+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":708,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-play_stacking_toy-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-play_stacking_toy-standard-s0-scene6.json"},{"created_at":"2026-10-16T04:23:31.934974+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":282,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-play_tic_tac_toe-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-play_tic_tac_toe-standard-s0-scene6.json"},{"created_at":"2026-10-15T21:21:58.993963+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":null,"native_controls":371,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-plug_in_charger-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-plug_in_charger-standard-s0-scene6.json"},{"created_at":"2026-10-15T21:18:24.002940+00:00","episode":{"capability":"Precision","scene":6,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":570,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-pour_balls_into_vase-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-pour_balls_into_vase-standard-s0-scene6.json"},{"created_at":"2026-10-16T03:54:25.398795+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-pour_by_language-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-pour_by_language-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:19:50.583924+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":359,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-pour_liquid_into_cup-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-pour_liquid_into_cup-random-s0-scene3.json"},{"created_at":"2026-10-15T21:00:14.165361+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":291,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-press_by_number-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-press_by_number-standard-s0-scene6.json"},{"created_at":"2026-10-15T21:13:30.884042+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":394,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-push_T-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-push_T-random-s0-scene3.json"},{"created_at":"2026-10-15T20:36:30.888266+00:00","episode":{"capability":"Long-Horizon","scene":6,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-put_bottles_into_dustbin-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-put_bottles_into_dustbin-standard-s0-scene6.json"},{"created_at":"2026-10-15T21:08:12.990795+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":164,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-solve_equation-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-solve_equation-standard-s0-scene6.json"},{"created_at":"2026-10-16T04:46:46.858421+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":913,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-sort_nesting_dolls_by_size-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-sort_nesting_dolls_by_size-random-s0-scene3.json"},{"created_at":"2026-10-15T21:22:04.457018+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":394,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-stack_blocks-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-stack_blocks-random-s0-scene3.json"},{"created_at":"2026-10-15T21:20:05.392254+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-stack_blocks_by_language-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-stack_blocks_by_language-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:50:18.130909+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":558,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-stack_bowls-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-stack_bowls-random-s0-scene3.json"},{"created_at":"2026-10-15T20:24:55.622158+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":484,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-store_laptop_and_headphones-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-store_laptop_and_headphones-random-s0-scene3.json"},{"created_at":"2026-10-16T04:06:39.161138+00:00","episode":{"capability":"Open","scene":6,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":825,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene6.json"},{"created_at":"2026-10-15T20:58:22.549758+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-swap_T-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-swap_T-standard-s0-scene6.json"},{"created_at":"2026-10-15T21:10:58.512140+00:00","episode":{"capability":"Memory","scene":6,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":580,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-swap_blocks-standard-s0-scene6","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-swap_blocks-standard-s0-scene6.json"},{"created_at":"2026-10-15T21:07:49.484458+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[7],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":814,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r7-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r7-mixed42-20261016-sweep_blocks-random-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r7-mixed42-20261016-sweep_blocks-random-s0-scene3.json"},{"created_at":"2026-10-15T18:33:27.127920+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":156,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-align_blocks-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-align_blocks-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:14:00.400968+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":405,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-arrange_largest_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-arrange_largest_number-standard-s0-scene3.json"},{"created_at":"2026-10-15T19:06:38.612743+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":885,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-build_tower-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-build_tower-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:16:51.451920+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":678,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-classify_objects-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-classify_objects-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:10:09.670030+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":680,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-classify_objects_by_language-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-classify_objects_by_language-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:03:06.681115+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":547,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-cover_blocks-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-cover_blocks-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:08:33.963219+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":253,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-deposit_coin-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-deposit_coin-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:01:43.841570+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":720,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-fasten_screws-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-fasten_screws-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:29:13.516351+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-fill_egg_holder-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-fill_egg_holder-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:50:18.702019+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":952,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-fill_pen_holder-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-fill_pen_holder-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:16:05.199620+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":null,"native_controls":416,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-fold_clothes-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-fold_clothes-standard-s0-scene3.json"},{"created_at":"2026-10-15T18:28:56.848070+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":16,"model_responses":16,"native_controls":106,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-general_pickup-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-general_pickup-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:38:16.001737+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":null,"native_controls":610,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-hang_mugs-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-hang_mugs-standard-s0-scene3.json"},{"created_at":"2026-10-15T19:58:17.665071+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":null,"native_controls":1444,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene7.json"},{"created_at":"2026-10-15T17:56:02.521003+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":281,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-insert_key-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-insert_key-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:18:30.951183+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":498,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-insert_tubes-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-insert_tubes-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:30:28.617977+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":518,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-make_kong-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-make_kong-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:28:22.580814+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":489,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-make_toast-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-make_toast-standard-s0-scene3.json"},{"created_at":"2026-10-15T19:16:47.585014+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":640,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:11:53.034208+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":659,"native_terminal":true,"score":0.75,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-organize_table-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-organize_table-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:07:46.572367+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1252,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-pack_objects_into_box-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-pack_objects_into_box-standard-s0-scene3.json"},{"created_at":"2026-10-15T19:08:00.237102+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":641,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:02:14.311903+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":null,"native_controls":477,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-play_Xylophone-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-play_Xylophone-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:34:00.094372+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":574,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-play_stacking_toy-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-play_stacking_toy-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:07:46.698935+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":837,"native_terminal":true,"score":0.75,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-play_tic_tac_toe-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-play_tic_tac_toe-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:09:49.317488+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":342,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-plug_in_charger-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-plug_in_charger-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:09:13.323431+00:00","episode":{"capability":"Precision","scene":7,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":427,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-pour_balls_into_vase-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-pour_balls_into_vase-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:32:37.671676+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":793,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-pour_by_language-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-pour_by_language-standard-s0-scene7.json"},{"created_at":"2026-10-15T17:52:05.345730+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":233,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-pour_liquid_into_cup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-pour_liquid_into_cup-standard-s0-scene3.json"},{"created_at":"2026-10-15T18:33:37.604887+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":279,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-press_by_number-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-press_by_number-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:21:23.850960+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":458,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-push_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-push_T-standard-s0-scene3.json"},{"created_at":"2026-10-15T18:24:31.063912+00:00","episode":{"capability":"Long-Horizon","scene":7,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":648,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-put_bottles_into_dustbin-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-put_bottles_into_dustbin-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:49:12.349765+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-solve_equation-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-solve_equation-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:00:05.064001+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":298,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-sort_nesting_dolls_by_size-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-sort_nesting_dolls_by_size-standard-s0-scene3.json"},{"created_at":"2026-10-15T18:10:32.395738+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":401,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-stack_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-stack_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-15T18:50:10.824756+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":376,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-stack_blocks_by_language-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-stack_blocks_by_language-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:53:46.511457+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":669,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-stack_bowls-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-stack_bowls-standard-s0-scene3.json"},{"created_at":"2026-10-15T18:47:56.341822+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":728,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-store_laptop_and_headphones-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-store_laptop_and_headphones-standard-s0-scene3.json"},{"created_at":"2026-10-15T19:43:21.983669+00:00","episode":{"capability":"Open","scene":7,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":882,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:35:02.929648+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-swap_T-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-swap_T-standard-s0-scene7.json"},{"created_at":"2026-10-15T18:43:33.369664+00:00","episode":{"capability":"Memory","scene":7,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":397,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-swap_blocks-standard-s0-scene7","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-swap_blocks-standard-s0-scene7.json"},{"created_at":"2026-10-15T19:11:43.893948+00:00","episode":{"capability":"Generalization","scene":3,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[8],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":643,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-medium-r8-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3-medium-r8-mixed42-20261016-sweep_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-medium-r8-mixed42-20261016-sweep_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-18T02:56:25.496688+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:27:26.136992+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":855,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-18T02:46:38.002732+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1019,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:49:38.003962+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":649,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-18T03:14:11.032074+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":950,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:52:52.455539+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":624,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-17T10:12:13.931759+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":278,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:48:40.057541+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:40:56.556106+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":285,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:51:53.572609+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":946,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:13:13.487407+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":412,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-18T02:52:36.680907+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":18,"model_responses":18,"native_controls":96,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:27:43.502052+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":765,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-18T03:14:07.872673+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":1323,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-17T10:02:45.248956+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":212,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-17T10:20:27.759999+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":404,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:55:21.136892+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":572,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:26:55.344373+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":747,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-18T02:44:09.183447+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":439,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:53:54.773607+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":799,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:27:40.244371+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":982,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-18T03:10:45.304717+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:28:02.864125+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":188,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:58:27.455779+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":797,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:50:34.870586+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":236,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-17T10:17:43.526893+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":336,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:23:40.869646+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":471,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-18T03:10:13.311760+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":702,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:13:43.090692+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":368,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-18T02:56:48.302957+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":336,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:32:50.788263+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":435,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-push_T-random-s0-scene0.json"},{"created_at":"2026-10-18T02:43:54.681672+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":577,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-18T03:00:37.704357+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:28:32.742026+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":740,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-18T02:26:24.785026+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":473,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-18T02:58:43.249656+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":282,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:25:58.060396+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":541,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-18T02:45:17.720894+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":692,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-18T03:17:22.499407+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":798,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:53:43.726056+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:46:12.928832+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":385,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-18T02:23:50.806299+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":723,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1-compact-precision4-20261017-v1-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-compact-precision4-20261017-v1-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-16T11:34:17.626654+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":248,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o1-precision4-20261016-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-precision4-20261016-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-precision4-20261016-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-16T12:02:41.606734+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":226,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o1-precision4-20261016-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-precision4-20261016-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-precision4-20261016-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-16T13:30:38.447927+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":72,"native_controls":486,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o1-precision4-20261016-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-precision4-20261016-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-precision4-20261016-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-16T11:50:13.551304+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":350,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-precision4-20261016-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-precision4-20261016-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-precision4-20261016-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-17T03:50:55.255382+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:43:03.675784+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":84,"native_controls":999,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:38:49.425163+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":667,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T12:29:27.008651+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":493,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-17T03:38:22.094772+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":74,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-17T07:12:16.945191+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1462,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:47:01.600583+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":98,"native_controls":395,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-17T03:55:20.501032+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":411,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:45:36.707302+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":94,"native_controls":714,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-17T04:10:05.696699+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":546,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-17T04:48:23.447068+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":590,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-16T12:36:00.063694+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":298,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-17T04:37:03.013280+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":514,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T12:19:01.765115+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":365,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-17T03:55:22.314477+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":353,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-17T03:55:42.026265+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-16T12:32:45.185184+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":486,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-17T03:57:10.202896+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":358,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-16T14:00:24.701369+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":737,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-16T12:22:56.564297+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":478,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-17T06:48:26.603265+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":98,"native_controls":869,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-17T03:53:46.697560+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-17T04:02:16.802368+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":410,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-16T12:20:35.439937+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":369,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-20261016-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-20261016-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-17T06:47:38.182710+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":641,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-17T05:55:13.822968+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":930,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:47:39.486639+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":900,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-17T05:45:32.300452+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":942,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:36:51.126555+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":642,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:25:08.344305+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":920,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-17T04:49:11.873336+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":475,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-17T06:46:57.551471+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":617,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-17T04:40:07.090432+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":577,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-17T05:30:13.581781+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":309,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-17T08:43:28.324611+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":256,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-17T05:57:48.990232+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":262,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-push_T-random-s0-scene0.json"},{"created_at":"2026-10-17T05:31:48.606245+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":688,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-17T05:12:34.346238+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-r1-mixed42-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":573,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-r1-mixed42-retry01-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1","score_scale":"0..1"},"run_id":"l3-o1-r1-mixed42-retry01-20261017-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1-r1-mixed42-retry01-20261017-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-24T06:17:55.314325+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":161,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:17:52.399200+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":164,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:16:46.124804+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":176,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:52:20.932462+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":961,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-24T07:42:02.004730+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":675,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-24T07:38:44.316777+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":435,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:35:42.097575+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":1024,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:37:04.671889+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":1036,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:31:36.829014+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":909,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-24T06:35:22.140588+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":1088,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:36:57.019760+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":905,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:40:25.559423+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1100,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-24T06:38:12.609089+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:33:27.764117+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":472,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:34:26.336758+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":672,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-24T06:52:05.730563+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":778,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:54:30.476414+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1017,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:54:09.091112+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1112,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:39:09.664646+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":314,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-24T07:35:01.961114+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":365,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-24T07:36:40.454440+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":332,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:38:40.577880+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":10,"model_responses":10,"native_controls":74,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:41:31.299136+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":16,"model_responses":16,"native_controls":113,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:44:39.227257+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":165,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:03:34.511292+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":1349,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:07:37.661308+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":1600,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:58:56.619599+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":1228,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-24T06:50:20.153277+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":446,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:59:09.827064+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":487,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:51:34.097499+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":325,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-24T08:01:37.265783+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1092,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-24T07:57:37.787820+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":1224,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-24T08:01:35.751292+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1018,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-24T06:50:26.057568+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":233,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:01:32.991917+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":561,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-24T06:54:14.563072+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":287,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:13:19.696988+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":462,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:11:05.863071+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":471,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:19:55.639709+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:10:24.671835+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":382,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:04:44.938359+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":331,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:07:46.148547+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":315,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:08:10.810804+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":396,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:14:22.098397+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":511,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:09:19.653218+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":282,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:15:37.603341+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":384,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:16:10.910213+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":354,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:15:35.413302+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":308,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:54:43.330017+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":432,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-push_T-random-s0-scene1.json"},{"created_at":"2026-10-24T07:52:38.336726+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":290,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-24T07:57:22.846598+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":380,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:23:43.608536+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":566,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:25:19.077354+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":637,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:28:36.218643+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":697,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:20:41.722678+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":207,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:20:52.388484+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":265,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:20:50.817854+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":221,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-24T07:57:17.623515+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":696,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-24T07:54:06.702268+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":684,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-24T08:00:05.076586+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":748,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:27:07.535901+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:24:18.475008+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":307,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:26:50.259933+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-24T08:05:29.858685+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":743,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-24T07:55:00.259952+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":468,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-24T08:15:52.574500+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":774,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:26:03.385954+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":389,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-24T07:27:54.405827+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":313,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:31:49.403260+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o1-compact-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":393,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o1-compact-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o1-compact","score_scale":"0..1"},"run_id":"l3-o1compact-devset-20261024-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o1compact-devset-20261024-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-17T06:13:15.049658+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e7f59eacb0acac77038d9d4eab8feaa00896bb8f1cfd6dd2a868d91f402c1b76","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o2-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":72,"native_controls":300,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o2-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o2","score_scale":"0..1"},"run_id":"l3-o2-precision4-20261017-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o2-precision4-20261017-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:03:35.985585+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e7f59eacb0acac77038d9d4eab8feaa00896bb8f1cfd6dd2a868d91f402c1b76","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o2-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":48,"native_controls":300,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o2-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o2","score_scale":"0..1"},"run_id":"l3-o2-precision4-20261017-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o2-precision4-20261017-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:30:46.004549+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e7f59eacb0acac77038d9d4eab8feaa00896bb8f1cfd6dd2a868d91f402c1b76","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o2-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":85,"native_controls":484,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o2-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o2","score_scale":"0..1"},"run_id":"l3-o2-precision4-20261017-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o2-precision4-20261017-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-17T06:07:47.901728+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e7f59eacb0acac77038d9d4eab8feaa00896bb8f1cfd6dd2a868d91f402c1b76","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o2-precision4-20261017-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":51,"native_controls":312,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o2-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o2","score_scale":"0..1"},"run_id":"l3-o2-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o2-precision4-20261017-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-19T04:01:19.912410+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":90,"native_controls":674,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a2-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a2-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-19T03:38:26.431818+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":284,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a2-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a2-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-19T03:45:04.990297+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":66,"native_controls":500,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a2-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a2-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-19T03:45:27.868615+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":310,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a2-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a2-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:50:46.202081+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":167,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T09:48:08.191388+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":912,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:48:46.386376+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":322,"native_terminal":true,"score":0.05,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T05:55:38.014362+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":329,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-19T08:44:20.602882+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":11,"native_controls":70,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-19T10:08:10.074869+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":1398,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:07:06.550551+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":94,"native_controls":439,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:47:18.057023+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":420,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:09:39.679778+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":96,"native_controls":794,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-19T09:42:13.045871+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:11:00.765075+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":694,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-19T05:53:28.712836+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":380,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-19T05:56:55.860601+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":392,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-19T09:24:40.105976+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":662,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:51:34.432198+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":294,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:51:32.314003+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":288,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:55:08.726266+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":360,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:05:16.756425+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":64,"native_controls":614,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-19T09:54:39.935517+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":761,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:46:09.108986+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":387,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:50:20.052937+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":421,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a3-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a3-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:32:43.983795+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":99,"native_controls":749,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-19T07:49:21.596975+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":913,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:50:40.519872+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":1113,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:30:39.449225+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":653,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:38:44.206754+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":73,"native_controls":668,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:18:41.962689+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":777,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-19T08:33:40.655967+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":82,"native_controls":625,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-19T08:06:50.652615+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":84,"native_controls":947,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-19T07:28:52.178813+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":253,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:57:50.070408+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-19T08:09:34.495567+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":96,"native_controls":232,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-push_T-random-s0-scene0.json"},{"created_at":"2026-10-19T07:39:31.627997+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":73,"native_controls":648,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:33:27.777009+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":82,"native_controls":787,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-19T07:08:31.794443+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":377,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-19T07:23:41.333267+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":690,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-19T08:19:12.711022+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":737,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-a4-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-a4-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-19T03:17:14.245255+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":300,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-20T11:24:14.443231+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":147,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:10:22.964502+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":149,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-20T15:40:09.901527+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":615,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-20T11:01:53.875994+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":658,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-20T16:19:31.092770+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":99,"native_controls":1082,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-20T15:18:18.439070+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":882,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:57:18.044009+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1086,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-20T11:28:53.387558+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":432,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:08:04.624407+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":86,"native_controls":527,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-20T11:06:36.418124+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":90,"native_controls":890,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:49:03.153133+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":94,"native_controls":1043,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-20T15:13:26.727893+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":70,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-20T10:34:19.280904+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":310,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-20T14:38:02.875922+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":10,"model_responses":10,"native_controls":63,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:05:58.086875+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":85,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-20T11:56:26.160614+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":82,"native_controls":1249,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-20T17:08:19.985941+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":1342,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-20T11:17:17.135106+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":444,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:48:41.757570+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":283,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-20T15:28:44.038351+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":969,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-20T11:10:13.565012+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1071,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-20T14:49:07.623078+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":367,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:28:35.493788+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":434,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-20T15:57:51.796482+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":81,"native_controls":390,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-20T10:55:16.460396+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":302,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:29:26.704850+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":314,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-20T11:12:52.082630+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":331,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:35:10.112625+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":334,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-20T11:14:53.837455+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":117,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:05:13.486716+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":302,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-20T15:24:48.678953+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":464,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-random-s0-scene1.json"},{"created_at":"2026-10-20T10:54:57.251866+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":86,"native_controls":275,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-20T11:19:08.584126+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":551,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:57:01.486346+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":67,"native_controls":695,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-20T20:33:46.299503+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":195,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-20T19:49:09.191667+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":65,"native_controls":387,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-20T19:52:57.473341+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":956,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-20T20:36:10.469623+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":932,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-20T21:05:47.652097+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":743,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-20T20:21:09.527364+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":66,"native_controls":431,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-20T20:18:15.680135+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":100,"native_controls":1086,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-20T19:32:54.124352+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":481,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-20T20:32:48.322413+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":79,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-20T21:26:22.635977+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1391,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-20T20:24:17.101207+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":305,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-20T19:44:55.037869+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":77,"native_controls":868,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-20T20:45:12.171109+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":231,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-20T19:42:31.692661+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":81,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-20T20:12:21.902844+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":64,"native_controls":382,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-20T19:54:50.706296+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":259,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-20T20:11:00.732236+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":67,"native_controls":600,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-20T20:26:25.981322+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":323,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-20T19:30:35.979615+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":137,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-20T20:24:53.384947+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":88,"native_controls":695,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-20T20:36:59.539020+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":177,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-20T20:12:06.073077+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":749,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-20T20:40:20.768187+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":369,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-20T19:51:29.786672+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":99,"native_controls":534,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-20T19:25:17.706021+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":315,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-20T20:27:09.832949+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-20T14:42:12.071087+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":179,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:22:36.428416+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":275,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-20T15:31:14.516280+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":83,"native_controls":720,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-20T10:56:18.305330+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":678,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-20T14:48:32.346006+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":370,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:17:03.463550+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":351,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-20T15:01:35.934258+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":67,"native_controls":516,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-20T10:56:37.695287+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":623,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-20T15:57:37.207024+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-depthpro-precision4-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":341,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-depthpro-precision4-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"l3-o23-depthpro-precision4-20261019-v1-p50supp1-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-depthpro-precision4-20261019-v1-p50supp1-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-23T09:22:33.646646+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-dynamic-gpu-20261023T160639-d299cf75-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-dynamic-gpu-20261023T160639-d299cf75-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:33:48.838823+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":128,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:21:57.917634+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":424,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-23T05:19:09.324082+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":938,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-23T06:59:29.586403+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":776,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-23T05:05:10.154249+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":436,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-23T06:11:53.036803+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":342,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-23T05:28:45.110611+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":79,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-23T06:35:25.694510+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":98,"native_controls":1458,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-23T04:17:02.789871+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":436,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:29:14.024999+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":432,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-23T07:04:40.823553+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":427,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-23T07:09:04.211893+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":76,"native_controls":367,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:29:09.748725+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":303,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-23T05:06:52.848153+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":489,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-push_T-random-s0-scene1.json"},{"created_at":"2026-10-23T04:19:22.866739+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":585,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-23T05:16:57.058284+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":74,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-23T04:12:05.443592+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":283,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-23T05:21:31.038608+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":189,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-23T05:44:50.363321+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":899,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-23T04:15:34.948738+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":376,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-23T04:45:06.646306+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":322,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-23T05:47:18.244934+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":100,"native_controls":742,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-23T04:13:26.054749+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":305,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-20261023-run3-d541ea2b-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-20261023-run3-d541ea2b-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-23T07:25:12.057036+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":113,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-independent-20261023T142520-286e4995-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-independent-20261023T142520-286e4995-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-23T07:23:11.737771+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":323,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-independent-20261023T142520-286e4995-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-independent-20261023T142520-286e4995-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-23T09:17:45.035543+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":97,"native_controls":355,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-independent-20261023T142520-286e4995-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-independent-20261023T142520-286e4995-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-23T08:59:02.725557+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":96,"native_controls":615,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-fresh36-independent-20261023T142520-286e4995-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-fresh36-independent-20261023T142520-286e4995-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-21T09:07:22.732980+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":144,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-21T10:45:38.771506+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-21T11:12:50.955628+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":89,"native_controls":567,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-21T09:28:36.010191+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":548,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-21T09:48:39.984041+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":91,"native_controls":903,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:28:34.184866+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":929,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-21T10:30:56.240586+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":1097,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:26:34.148017+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":943,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-21T09:50:36.626187+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":425,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:07:29.026918+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":72,"native_controls":420,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-21T09:37:13.571157+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":80,"native_controls":887,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:00:55.730327+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":377,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-21T11:04:19.163733+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":452,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-21T09:25:32.273972+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-21T09:39:05.072916+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":10,"model_responses":10,"native_controls":63,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-21T10:56:16.306237+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":16,"model_responses":16,"native_controls":141,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-21T10:46:56.979356+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":98,"native_controls":1394,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-21T09:53:13.566816+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":377,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:25:02.212269+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":70,"native_controls":342,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-21T11:28:05.729892+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":532,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-21T10:06:55.897823+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":75,"native_controls":847,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-21T10:03:33.148444+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":314,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:21:30.277116+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":291,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-21T10:27:35.473533+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":86,"native_controls":456,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:32:16.250332+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":317,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-21T10:10:11.699663+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":305,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:38:45.670839+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":384,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-21T10:20:56.260424+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":418,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:35:33.211360+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":184,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-21T10:23:44.041752+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":385,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-21T11:42:00.257775+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":342,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-21T10:27:16.223592+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":67,"native_controls":209,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-21T10:29:24.941504+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":563,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-21T10:31:31.827981+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":173,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-21T10:43:30.315431+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":616,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-21T10:42:36.891897+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":354,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-21T10:46:17.294350+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":408,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-21T10:42:34.079600+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":368,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-devset-20261021-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-devset-20261021-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-18T06:06:43.857089+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":null,"native_controls":162,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:47:06.402519+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":99,"native_controls":753,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-18T08:07:28.101281+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":701,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:50:24.184975+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":887,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-17T15:02:41.826727+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":76,"native_controls":918,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:25:35.353920+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":429,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-18T09:54:39.360194+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":1061,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:47:08.043035+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":586,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:12:05.448785+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":null,"native_controls":971,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:51:33.946892+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":416,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-17T14:16:32.852274+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":84,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:45:29.903576+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":91,"native_controls":699,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-17T15:02:20.684454+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1465,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-18T09:52:59.137537+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":576,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-17T15:03:49.585500+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":90,"native_controls":756,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-18T08:36:19.251657+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":325,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:58:34.615845+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":91,"native_controls":722,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:38:44.984576+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":88,"native_controls":951,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-18T08:06:34.208225+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":null,"native_controls":338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:34:33.269387+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":77,"native_controls":426,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:18:56.081621+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":926,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-17T15:09:20.092251+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":209,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-17T15:03:16.378739+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":307,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:20:39.611139+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":null,"native_controls":777,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:23:01.574862+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":310,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-18T09:59:28.031615+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":323,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:50:48.617409+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":187,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-push_T-random-s0-scene0.json"},{"created_at":"2026-10-17T14:29:44.510585+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":684,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:22:47.328132+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":286,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:25:59.353237+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":null,"native_controls":458,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-17T14:32:56.421009+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":341,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-18T08:20:30.732951+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":292,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:34:13.947717+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":72,"native_controls":605,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-17T14:28:45.437047+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":523,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-18T09:20:24.443680+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":813,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:47:09.936291+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":392,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-17T14:43:51.461425+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:07:40.916585+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":null,"native_controls":777,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-full-ik42-medium-r1-20261017-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-full-ik42-medium-r1-20261017-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-23T12:46:07.375194+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":99,"native_controls":1120,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-graphics51-20261023T195942-10dd112b-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-graphics51-20261023T195942-10dd112b-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-23T09:22:21.642184+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":394,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-native-wait-20261023T151947-292d3cc8-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-native-wait-20261023T151947-292d3cc8-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-17T10:38:32.500401+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":300,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-precision4-20261017-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-precision4-20261017-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-17T10:31:34.362054+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":231,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-precision4-20261017-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-precision4-20261017-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-17T11:08:40.363154+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":472,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-precision4-20261017-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-precision4-20261017-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-17T11:29:01.775959+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":90,"native_controls":304,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23-precision4-20261017-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-precision4-20261017-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-23T12:02:55.561716+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23-full-ik42-medium-r1-20261017","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":1221,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23-full-ik42-medium-r1-20261017","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"},"run_id":"l3-o23-transport-restart-20261023T163714-ff793d1e-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23-transport-restart-20261023T163714-ff793d1e-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-23T07:10:18.848226+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-23T17:29:34.194062+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":93,"native_controls":622,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-23T22:18:42.163985+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":98,"native_controls":657,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-23T17:30:34.747370+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":100,"native_controls":879,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-23T18:06:53.926882+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":864,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-23T19:42:51.314492+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":85,"native_controls":443,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-23T07:30:22.261213+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":279,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-23T21:54:14.289553+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":98,"native_controls":545,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-23T15:27:24.741906+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":61,"native_controls":336,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-23T17:11:01.517127+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":97,"native_controls":839,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-23T18:37:56.755541+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":55,"native_controls":393,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-23T04:30:48.897738+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":11,"native_controls":69,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-23T18:03:39.869635+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":97,"native_controls":611,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-23T19:26:38.596434+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":103,"native_controls":1245,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-23T05:09:50.243546+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":217,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-23T19:33:54.656342+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":62,"native_controls":467,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-23T17:43:58.099138+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":414,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-23T18:44:26.518366+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":100,"native_controls":598,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-23T17:27:09.978927+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":296,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-23T17:53:35.029391+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":98,"native_controls":638,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-23T17:38:13.181354+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":1135,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-23T22:11:15.552825+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":410,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-23T17:59:27.426939+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":101,"native_controls":535,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-23T18:18:20.761354+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":100,"native_controls":243,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-23T20:23:09.538811+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":72,"native_controls":333,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-23T19:40:46.294925+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":70,"native_controls":600,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-23T16:02:33.479185+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":84,"native_controls":758,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-23T18:28:10.394855+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":251,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-23T15:57:35.992669+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":69,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-push_T-random-s0-scene0.json"},{"created_at":"2026-10-23T15:43:31.145911+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":94,"native_controls":700,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-23T17:42:32.523307+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-sim51-recovery1-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-sim51-recovery1-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-23T22:03:54.071570+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":89,"native_controls":613,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-sim60-recovery1-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-sim60-recovery1-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-23T05:18:04.030102+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":202,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-23T21:32:07.912566+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":758,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-23T15:19:36.361208+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":69,"native_controls":378,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-23T14:43:47.064049+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":63,"native_controls":352,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-24T04:15:58.471220+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":null,"native_controls":619,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-23T21:29:30.564485+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":102,"native_controls":768,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-23T17:48:09.950708+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":87,"native_controls":595,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-23T14:44:10.124347+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":48,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-23T15:34:25.599282+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":74,"native_controls":421,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-23T18:16:12.800586+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-clear-full42-20261023-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":null,"native_controls":632,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-clear-full42-20261023-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-clear","score_scale":"0..1"},"run_id":"l3-o23456-clear-full42-20261023-v1-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-clear-full42-20261023-v1-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-20T19:26:40.132835+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"0cdde47219da48d5a2af5a18a610949135d388f3f9f601fb82207f79ff957f3c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-generation-precision1-20261021-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":null,"native_controls":281,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23456-generation-precision1-20261021-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-generation","score_scale":"0..1"},"run_id":"l3-o23456-generation-precision1-20261021-v1-initretry01-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-generation-precision1-20261021-v1-initretry01-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-20T22:44:12.821134+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":563,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-20T20:26:36.997844+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":456,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-20T23:54:13.132237+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":637,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-21T03:54:01.825582+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":609,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-20T22:59:40.604919+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":867,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-20T19:57:23.968098+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":371,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-21T04:41:09.949212+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":524,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-push_T-random-s0-scene0.json"},{"created_at":"2026-10-21T01:32:17.548775+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":674,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-20T20:58:26.437801+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-20T20:49:47.019992+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":613,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-21T02:45:38.590086+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":884,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-generalization12-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-generalization12-20261020-v1-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-generalization12-20261020-v1-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-20T23:24:58.576086+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":635,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-precision8-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-precision8-20261020-v1-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-precision8-20261020-v1-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-20T18:06:18.669628+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":248,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-precision8-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-precision8-20261020-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-precision8-20261020-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-21T01:27:25.218542+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":896,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-precision8-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-precision8-20261020-v1-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-precision8-20261020-v1-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-20T18:15:43.736494+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":285,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-precision8-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-precision8-20261020-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-precision8-20261020-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-20T21:43:49.291511+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":475,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-precision8-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-precision8-20261020-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-precision8-20261020-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-20T22:03:37.618530+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":336,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-precision8-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-precision8-20261020-v1-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-precision8-20261020-v1-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-20T21:26:46.900699+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":341,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-precision8-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-precision8-20261020-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-precision8-20261020-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-20T20:09:32.260378+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o23456-pure-20261020","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":533,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o23456-pure-precision8-20261020-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"},"run_id":"l3-o23456-pure-precision8-20261020-v1-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o23456-pure-precision8-20261020-v1-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-17T18:55:25.144708+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"53f2c14091824b5686890ec91ff23b8a5f1eab741789413c19b66d8758a460c3","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o4-precision4-20261018-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":271,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o4-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o4","score_scale":"0..1"},"run_id":"l3-o4-precision4-20261018-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o4-precision4-20261018-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-17T18:46:57.124877+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"53f2c14091824b5686890ec91ff23b8a5f1eab741789413c19b66d8758a460c3","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o4-precision4-20261018-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":239,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o4-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o4","score_scale":"0..1"},"run_id":"l3-o4-precision4-20261018-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o4-precision4-20261018-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-17T19:21:01.455320+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"53f2c14091824b5686890ec91ff23b8a5f1eab741789413c19b66d8758a460c3","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o4-precision4-20261018-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":62,"native_controls":480,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o4-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o4","score_scale":"0..1"},"run_id":"l3-o4-precision4-20261018-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o4-precision4-20261018-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-17T19:44:45.884538+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"53f2c14091824b5686890ec91ff23b8a5f1eab741789413c19b66d8758a460c3","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o4-precision4-20261018-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":90,"native_controls":389,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o4-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o4","score_scale":"0..1"},"run_id":"l3-o4-precision4-20261018-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o4-precision4-20261018-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:25:06.100282+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"37554043e6e2baf373de820f2a03adef34af89f64e7746ab71cbe0dba7d8eb7c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o45-precision4-20261018-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":48,"native_controls":277,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o45-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o45","score_scale":"0..1"},"run_id":"l3-o45-precision4-20261018-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o45-precision4-20261018-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:06:29.309764+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"37554043e6e2baf373de820f2a03adef34af89f64e7746ab71cbe0dba7d8eb7c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o45-precision4-20261018-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":42,"native_controls":272,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o45-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o45","score_scale":"0..1"},"run_id":"l3-o45-precision4-20261018-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o45-precision4-20261018-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-18T09:28:42.016957+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"37554043e6e2baf373de820f2a03adef34af89f64e7746ab71cbe0dba7d8eb7c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o45-precision4-20261018-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":66,"native_controls":500,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o45-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o45","score_scale":"0..1"},"run_id":"l3-o45-precision4-20261018-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o45-precision4-20261018-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-18T08:54:53.717539+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"37554043e6e2baf373de820f2a03adef34af89f64e7746ab71cbe0dba7d8eb7c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o45-precision4-20261018-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":57,"native_controls":295,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o45-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o45","score_scale":"0..1"},"run_id":"l3-o45-precision4-20261018-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o45-precision4-20261018-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-19T17:32:17.266763+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":null,"native_controls":688,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-19T08:11:08.325586+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":309,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-19T06:56:08.232270+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":276,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-19T12:13:27.041607+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":null,"native_controls":466,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-19T15:08:31.444293+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":882,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-19T07:07:38.179306+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":386,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-19T17:17:00.718019+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":530,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-push_T-random-s0-scene0.json"},{"created_at":"2026-10-19T17:32:15.479150+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":747,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-19T07:08:37.101889+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-19T13:26:33.174015+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":null,"native_controls":418,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-19T07:13:23.196535+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":340,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-19T12:18:39.179053+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":553,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-generalization12-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-generalization12-20261019-v1-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-generalization12-20261019-v1-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-20T14:07:17.643527+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":129,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-20T18:27:26.308646+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-20T20:57:54.431727+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":166,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-20T19:29:35.658463+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1004,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-20T23:49:26.670569+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":814,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-20T19:55:44.814949+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":83,"native_controls":751,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-21T02:49:48.553774+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":716,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-20T20:24:57.891090+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":82,"native_controls":422,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-21T00:08:05.783841+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":407,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-21T09:57:58.551054+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":81,"native_controls":425,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-20T14:58:31.895927+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":11,"native_controls":63,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:53:54.072455+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":92,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-20T19:18:18.860618+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":82,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:40:34.370410+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":316,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-20T21:19:50.197984+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":515,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-20T23:02:56.792210+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":313,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:41:21.389672+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":310,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-20T21:40:35.933674+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":81,"native_controls":661,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-21T06:32:12.629864+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":81,"native_controls":629,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:12:06.682814+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":341,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-20T18:34:51.522164+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":366,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-20T21:01:48.239378+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":321,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-20T15:28:14.633795+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":443,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-20T19:50:22.967987+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":699,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-21T01:43:52.538503+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":100,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:00:48.505602+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":152,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-20T18:27:52.952943+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":289,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-20T20:54:12.865856+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":173,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:55:22.905700+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-20T19:31:40.536169+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-20T21:43:02.593112+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":323,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-20T17:47:01.305248+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":387,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-20T20:48:12.535794+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":321,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-21T00:00:50.455004+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-20T05:07:50.432859+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":null,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T18:52:44.992346+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":89,"native_controls":853,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-20T14:25:46.970371+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":null,"native_controls":709,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-19T18:00:13.013855+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":432,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T19:10:44.782180+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":82,"native_controls":608,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-20T14:14:01.896974+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":820,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:53:51.276041+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":71,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-20T19:54:55.367335+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":null,"native_controls":1279,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-19T18:36:15.781337+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":298,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-19T14:56:26.434132+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":326,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-19T17:34:31.499397+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":457,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-20T12:25:54.159539+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":null,"native_controls":562,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-19T18:27:33.529458+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":75,"native_controls":545,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-20T12:33:10.839580+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":234,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-19T19:17:04.946638+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":769,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:09:32.543037+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":null,"native_controls":349,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-19T17:38:59.487740+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:26:17.902066+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":null,"native_controls":276,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-20T10:36:49.952578+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":null,"native_controls":317,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-20T14:25:13.155557+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":null,"native_controls":651,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:48:40.397952+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-20T07:56:53.824067+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":448,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-olm22-medium-r1-20261019-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-olm22-medium-r1-20261019-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-18T17:44:50.227082+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":300,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-precision4-20261018-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-precision4-20261018-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-18T17:34:16.145111+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":276,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-precision4-20261018-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-precision4-20261018-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-18T20:08:54.481869+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-precision4-20261018-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-precision4-20261018-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-18T20:49:36.930613+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":388,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-precision4-20261018-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-precision4-20261018-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-precision4-20261018-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-18T23:05:48.537890+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":80,"native_controls":679,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-precision8-completion-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-precision8-completion-20261019-v1-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-precision8-completion-20261019-v1-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-18T23:20:17.166016+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":83,"native_controls":513,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-precision8-completion-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-precision8-completion-20261019-v1-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-precision8-completion-20261019-v1-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-18T23:01:40.272174+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":379,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-precision8-completion-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-precision8-completion-20261019-v1-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-precision8-completion-20261019-v1-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-18T19:45:15.446208+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":391,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-precision8-completion-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-clear-precision8-completion-20261019-v1-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-clear-precision8-completion-20261019-v1-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-25T15:35:52.435578+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-complement30-20261025-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-complement30-20261025-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-25T13:46:44.195300+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":370,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-complement30-20261025-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-complement30-20261025-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-25T14:55:17.095803+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":319,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-complement30-20261025-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-complement30-20261025-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-25T13:33:06.059461+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":399,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-complement30-20261025-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-complement30-20261025-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-25T14:31:44.030963+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":495,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-complement30-20261025-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-complement30-20261025-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-23T22:17:56.403138+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":75,"native_controls":977,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-o456-repaired-20261024T000632-e66c6663-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-o456-repaired-20261024T000632-e66c6663-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-23T20:51:20.098708+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":483,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-o456-repaired-20261024T000632-e66c6663-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-o456-repaired-20261024T000632-e66c6663-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-23T23:40:45.638398+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":1306,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-23T23:51:37.912915+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1381,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-23T23:03:35.350425+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":89,"native_controls":1281,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-26T22:16:59.075073+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":341,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-refill12-20261027T030000-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-refill12-20261027T030000-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-26T22:26:09.494075+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":343,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-refill12-20261027T030000-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-refill12-20261027T030000-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-27T01:45:55.835843+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":88,"native_controls":875,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-refill12-20261027T030000-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-refill12-20261027T030000-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-26T22:38:27.402600+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":600,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-refill12-20261027T030000-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-refill12-20261027T030000-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-26T21:48:44.489221+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":259,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-refill12-20261027T030000-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-refill12-20261027T030000-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-27T00:17:55.242944+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":430,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-refill12-20261027T030000-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-refill12-20261027T030000-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-27T00:46:58.564531+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":442,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-refill12-20261027T030000-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-refill12-20261027T030000-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-26T19:48:25.632077+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":86,"native_controls":526,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-26T18:40:02.512787+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":550,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-26T16:19:19.374982+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":286,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-26T23:27:22.271964+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":85,"native_controls":710,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-26T18:04:29.740864+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":409,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-26T20:26:12.452516+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1046,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-26T18:35:35.927932+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":null,"native_controls":484,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-26T18:10:44.094403+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":448,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-26T19:21:16.005895+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":477,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-26T22:51:19.601955+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":364,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-26T16:41:17.312062+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-26T20:56:14.834202+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-26T16:15:24.702614+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":374,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-26T21:11:00.797958+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":84,"native_controls":216,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-push_T-random-s0-scene1.json"},{"created_at":"2026-10-26T19:16:35.229719+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":391,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-26T21:41:36.115865+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":75,"native_controls":837,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-26T22:29:13.800351+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":501,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-26T18:44:07.189211+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-o456-clear-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":419,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-o456-clear-olm22-medium-r1-20261019","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"},"run_id":"l3-o456-remainder12-20261026T213800-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-o456-remainder12-20261026T213800-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:09:33.364178+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:22:23.368731+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":724,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-19T13:46:03.809081+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":null,"native_controls":898,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:38:47.218050+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":936,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:38:43.089402+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":1075,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:58:08.470595+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":517,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:18:25.921639+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":242,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-19T14:06:45.468323+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1308,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:24:43.996931+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:01:10.703263+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":298,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-20T03:35:26.944974+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":723,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-20T06:25:12.280798+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":778,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-20T06:07:37.116286+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":16,"model_responses":16,"native_controls":120,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-20T06:29:47.972202+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":1383,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-20T06:23:43.403651+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":666,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-20T06:13:06.039315+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":238,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-20T06:13:38.171202+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":294,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-20T06:16:40.138041+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":408,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-20T06:20:48.798418+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":762,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-20T06:31:12.265155+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":900,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-19T08:18:39.381031+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":264,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-19T12:23:35.596290+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":494,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:02:55.289672+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":531,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:53:39.258198+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":402,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:59:44.669644+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":887,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:20:23.789533+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":1055,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-19T14:17:18.124475+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":446,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:25:06.820728+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":788,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:27:31.613222+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":230,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-19T11:56:17.194494+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":null,"native_controls":340,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-19T11:59:56.057752+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":null,"native_controls":426,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:08:01.745645+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":633,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-20T02:57:18.947831+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":315,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-20T03:59:00.240959+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":256,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:14:20.863196+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":363,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-push_T-random-s0-scene0.json"},{"created_at":"2026-10-20T03:13:07.543187+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:27:32.684060+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":869,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-20T03:52:26.211981+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":280,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:09:37.270337+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":457,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-20T04:01:45.239866+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-20T04:09:54.887972+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":545,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-20T03:18:02.662475+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":822,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"l3-r1-keyframes-precision8-20261019-v1-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r1-keyframes-precision8-20261019-v1-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-20T08:51:55.775370+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":172,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:31:40.450984+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":922,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-19T07:38:14.364043+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":973,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:53:55.292415+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1088,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-20T09:36:15.804154+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":929,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:40:56.944711+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":472,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:23:48.482991+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":269,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:28:44.740831+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":938,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:51:28.591452+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:39:43.438587+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":1075,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:10:34.211369+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":308,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-20T08:50:48.286073+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":81,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:22:09.781225+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":707,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-20T10:16:31.633519+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1512,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-20T09:56:01.074739+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":295,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-holdretry1-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-holdretry1-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-20T09:52:41.745462+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-holdretry1-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-holdretry1-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:16:53.099830+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":286,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:10:19.364137+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":490,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-20T09:03:48.810405+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":576,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:51:10.001516+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":927,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-20T08:55:01.233314+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":585,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-20T09:02:00.984343+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":891,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:23:09.213497+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":919,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-20T09:10:00.459210+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":523,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-19T07:21:03.126289+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-20T09:17:30.561110+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":762,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:51:00.055211+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":272,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:41:15.277503+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-19T06:35:21.250423+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":563,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-20T09:21:52.491983+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":663,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:19:14.805362+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-20T08:32:01.680720+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":380,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-push_T-random-s0-scene0.json"},{"created_at":"2026-10-20T08:23:08.511461+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:57:48.691501+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:35:48.333652+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":913,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-20T08:16:20.976568+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":344,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-20T08:58:03.410468+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":380,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:14:09.049053+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":587,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-20T08:19:14.110434+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":595,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-20T09:42:52.634396+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":896,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:55:30.156404+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":456,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-20T08:27:55.101380+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":830,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"l3-r2-precision8-20261019-v1-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3-r2-precision8-20261019-v1-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-12T10:07:55.016654+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"low-cap20-rounds8-infra-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"low"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":739,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-low-mixed42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_low_stack_bowls_random_s0_scene0_20261012","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_low_stack_bowls_random_s0_scene0_20261012.json"},{"created_at":"2026-10-05T22:30:10.938411Z","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":197,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_align_blocks_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_align_blocks_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:09:01.892547Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":667,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_arrange_largest_number_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_arrange_largest_number_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:23:12.917577Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":500,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_arrange_largest_number_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_arrange_largest_number_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:25:58.617869Z","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":799,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_build_tower_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_build_tower_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:05:24.783918Z","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":961,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_classify_objects_by_language_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_classify_objects_by_language_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:12:37.229134Z","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":911,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_classify_objects_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_classify_objects_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:02:18.131509Z","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":784,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_cover_blocks_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_cover_blocks_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:35:19.922921Z","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":286,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_deposit_coin_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_deposit_coin_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:01:52.008795Z","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1067,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_fasten_screws_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_fasten_screws_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:19:12.288338Z","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":695,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_fill_egg_holder_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_fill_egg_holder_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:04:21.384835Z","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":971,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_fill_pen_holder_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_fill_pen_holder_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:46:52.958555Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":410,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_fold_clothes_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_fold_clothes_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T20:08:47.037051Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":327,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_fold_clothes_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_fold_clothes_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:21:31.664831Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":771,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_hang_mugs_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_hang_mugs_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:42:51.429651Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":643,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_hang_mugs_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_hang_mugs_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T20:51:52.796573Z","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":1390,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_imitate_sorting_sequence_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_imitate_sorting_sequence_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:37:42.586293Z","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":270,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_insert_key_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_insert_key_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T20:18:02.243611Z","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":417,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_insert_tubes_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_insert_tubes_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:07:31.019395Z","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":449,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_make_kong_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_make_kong_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:02:49.125438Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":741,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_make_toast_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_make_toast_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:27:25.272919Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":771,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_make_toast_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_make_toast_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:18:00.608473Z","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":604,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_match_and_pick_from_conveyor_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_match_and_pick_from_conveyor_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:06:01.785497Z","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":897,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_organize_table_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_organize_table_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T20:56:16.260388Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":1066,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_pack_objects_into_box_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_pack_objects_into_box_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T10:58:27.885278Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":1026,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_pack_objects_into_box_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_pack_objects_into_box_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:45:51.866828Z","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":275,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_pick_from_conveyor_by_image_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_pick_from_conveyor_by_image_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:07:47.507121Z","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":495,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_play_Xylophone_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_play_Xylophone_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T20:56:19.858978Z","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":486,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_play_stacking_toy_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_play_stacking_toy_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:45:02.637308Z","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":261,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_play_tic_tac_toe_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_play_tic_tac_toe_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:11:09.907699Z","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":319,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_plug_in_charger_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_plug_in_charger_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:13:09.039169Z","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":506,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_pour_balls_into_vase_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_pour_balls_into_vase_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T20:51:56.730544Z","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":394,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_pour_by_language_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_pour_by_language_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:27:19.530577Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":396,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_pour_liquid_into_cup_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_pour_liquid_into_cup_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:12:58.376847Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":316,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_pour_liquid_into_cup_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_pour_liquid_into_cup_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:37:44.339368Z","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_press_by_number_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_press_by_number_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:36:42.411789Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":211,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_push_T_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_push_T_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:29:08.875843Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":499,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_push_T_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_push_T_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:44:47.936708Z","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":679,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_put_bottles_into_dustbin_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_put_bottles_into_dustbin_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-08T11:36:08.566251Z","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":155,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_align_blocks_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_align_blocks_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:19:37.112082Z","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_align_blocks_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_align_blocks_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:36:36.672493Z","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_align_blocks_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_align_blocks_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T14:57:28.587710Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":531,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_arrange_largest_number_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_arrange_largest_number_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T11:55:14.301425Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":440,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_arrange_largest_number_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_arrange_largest_number_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T16:07:10.294383Z","episode":{"capability":"Precision","scene":1,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":896,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_build_tower_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_build_tower_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:55:29.805203Z","episode":{"capability":"Precision","scene":2,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":738,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_build_tower_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_build_tower_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T08:31:05.243715Z","episode":{"capability":"Precision","scene":3,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1016,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_build_tower_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_build_tower_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T13:08:36.753615Z","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":1095,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:10:47.931950Z","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:36:37.006830Z","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":1095,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T15:53:55.933101Z","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":890,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_classify_objects_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_classify_objects_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T20:04:04.968611Z","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":949,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_classify_objects_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_classify_objects_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T08:12:58.325810Z","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":942,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_classify_objects_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_classify_objects_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T10:21:06.419249Z","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":442,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_cover_blocks_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_cover_blocks_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:31:51.219805Z","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_cover_blocks_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_cover_blocks_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:35:27.688995Z","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":721,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_cover_blocks_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_cover_blocks_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T09:26:17.342870Z","episode":{"capability":"Precision","scene":1,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":274,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_deposit_coin_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_deposit_coin_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:08:53.299081Z","episode":{"capability":"Precision","scene":2,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":268,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_deposit_coin_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_deposit_coin_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-08T20:48:55.611984Z","episode":{"capability":"Precision","scene":3,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":238,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_deposit_coin_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_deposit_coin_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T12:55:45.503778Z","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1261,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fasten_screws_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fasten_screws_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:25:37.647070Z","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1101,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fasten_screws_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fasten_screws_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T08:03:34.358230Z","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1089,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fasten_screws_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fasten_screws_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T12:59:43.153070Z","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":698,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fill_egg_holder_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fill_egg_holder_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:36:00.195967Z","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":659,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fill_egg_holder_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fill_egg_holder_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:21:04.364038Z","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":670,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fill_egg_holder_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fill_egg_holder_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T12:56:02.192763Z","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":982,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fill_pen_holder_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fill_pen_holder_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:20:44.742726Z","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1053,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fill_pen_holder_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fill_pen_holder_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-08T21:03:31.993893Z","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":594,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fill_pen_holder_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fill_pen_holder_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T13:03:17.337440Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":464,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fold_clothes_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fold_clothes_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T09:30:32.408535Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":349,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_fold_clothes_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_fold_clothes_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T09:17:43.946865Z","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":140,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_general_pickup_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_general_pickup_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T17:48:06.474974Z","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":198,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_general_pickup_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_general_pickup_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-08T20:44:15.354523Z","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":121,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_general_pickup_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_general_pickup_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T16:01:01.821923Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":797,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_hang_mugs_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_hang_mugs_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T12:54:01.152266Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":682,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_hang_mugs_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_hang_mugs_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T15:32:59.274929Z","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1474,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:43:00.228516Z","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1510,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T08:03:28.827465Z","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":1361,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T10:06:01.133799Z","episode":{"capability":"Precision","scene":1,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":220,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_insert_key_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_insert_key_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:00:10.976418Z","episode":{"capability":"Precision","scene":2,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":294,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_insert_key_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_insert_key_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-08T20:41:59.417701Z","episode":{"capability":"Precision","scene":3,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":247,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_insert_key_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_insert_key_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T10:16:12.963783Z","episode":{"capability":"Precision","scene":1,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":500,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_insert_tubes_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_insert_tubes_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:00:07.112562Z","episode":{"capability":"Precision","scene":2,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":424,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_insert_tubes_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_insert_tubes_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:02:51.205443Z","episode":{"capability":"Precision","scene":3,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_insert_tubes_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_insert_tubes_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T13:05:26.771242Z","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":373,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_make_kong_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_make_kong_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:20:40.134148Z","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":571,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_make_kong_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_make_kong_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:55:25.002286Z","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":456,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_make_kong_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_make_kong_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T10:32:36.721769Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":468,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_make_toast_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_make_toast_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T14:57:26.547659Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":469,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_make_toast_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_make_toast_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T13:01:19.520829Z","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":396,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T20:03:45.809470Z","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":506,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:54:16.334466Z","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":331,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T15:35:36.133879Z","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":null,"native_controls":662,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_organize_table_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_organize_table_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T20:10:30.472881Z","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":924,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_organize_table_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_organize_table_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T08:23:12.055956Z","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":811,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_organize_table_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_organize_table_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T10:24:38.590959Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":579,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pack_objects_into_box_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pack_objects_into_box_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T15:32:41.967313Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1113,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pack_objects_into_box_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pack_objects_into_box_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T09:57:22.622028Z","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":256,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:02:19.473974Z","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:03:03.124625Z","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":486,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T11:56:01.769514Z","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":389,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_Xylophone_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_Xylophone_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:49:06.198653Z","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":388,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_Xylophone_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_Xylophone_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:20:57.567036Z","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":334,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_Xylophone_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_Xylophone_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T12:59:21.394630Z","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":643,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_stacking_toy_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_stacking_toy_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:40:04.879237Z","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":563,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_stacking_toy_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_stacking_toy_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:32:39.241187Z","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":612,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_stacking_toy_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_stacking_toy_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T14:58:40.882852Z","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":360,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_tic_tac_toe_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_tic_tac_toe_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:48:23.556379Z","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":321,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_tic_tac_toe_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_tic_tac_toe_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T08:17:24.906908Z","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":275,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_play_tic_tac_toe_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_play_tic_tac_toe_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T11:33:12.974173Z","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":371,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_plug_in_charger_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_plug_in_charger_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:56:45.829016Z","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":376,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_plug_in_charger_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_plug_in_charger_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:22:20.972774Z","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":333,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_plug_in_charger_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_plug_in_charger_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T11:34:55.857435Z","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":511,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:11:33.341623Z","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":593,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:35:20.433306Z","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":563,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T10:15:41.629448Z","episode":{"capability":"Open","scene":1,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":648,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pour_by_language_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pour_by_language_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:25:12.296704Z","episode":{"capability":"Open","scene":2,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pour_by_language_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pour_by_language_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:01:21.332848Z","episode":{"capability":"Open","scene":3,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pour_by_language_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pour_by_language_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T09:21:23.708065Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":274,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pour_liquid_into_cup_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pour_liquid_into_cup_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T12:13:07.159439Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_pour_liquid_into_cup_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_pour_liquid_into_cup_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T11:43:52.029270Z","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":155,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_press_by_number_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_press_by_number_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:56:42.824792Z","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":106,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_press_by_number_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_press_by_number_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:47:00.310711Z","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":317,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_press_by_number_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_press_by_number_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T09:59:48.695558Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":138,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_push_T_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_push_T_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T10:10:06.812300Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":340,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_push_T_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_push_T_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T10:30:39.555682Z","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":700,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:53:45.369676Z","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":684,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:02:48.317183Z","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":696,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T09:16:07.045612Z","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":217,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_solve_equation_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_solve_equation_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T17:56:36.465186Z","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":282,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_solve_equation_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_solve_equation_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-08T20:42:07.402372Z","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":180,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_solve_equation_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_solve_equation_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T15:55:23.921705Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":870,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_sort_nesting_dolls_by_size_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_sort_nesting_dolls_by_size_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T15:45:48.347744Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":731,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_sort_nesting_dolls_by_size_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_sort_nesting_dolls_by_size_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T10:03:56.497244Z","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:11:33.015762Z","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-08T21:00:13.770025Z","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":398,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T15:00:13.664262Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":396,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_stack_blocks_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_stack_blocks_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T09:22:36.193261Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":205,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_stack_blocks_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_stack_blocks_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T11:18:02.342234Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":631,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_stack_bowls_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_stack_bowls_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T15:44:31.574173Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":575,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_stack_bowls_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_stack_bowls_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T14:56:43.779151Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":703,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_store_laptop_and_headphones_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_store_laptop_and_headphones_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T15:01:37.337028Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":782,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_store_laptop_and_headphones_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_store_laptop_and_headphones_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T15:21:33.615067Z","episode":{"capability":"Open","scene":1,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":788,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_store_tools_in_toolbox_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_store_tools_in_toolbox_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T20:00:34.496439Z","episode":{"capability":"Open","scene":2,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":816,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_store_tools_in_toolbox_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_store_tools_in_toolbox_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T08:20:21.388024Z","episode":{"capability":"Open","scene":3,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":900,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_store_tools_in_toolbox_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_store_tools_in_toolbox_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T12:59:50.100474Z","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":350,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_swap_T_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_swap_T_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T19:31:06.040551Z","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":295,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_swap_T_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_swap_T_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:52:06.766685Z","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":388,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_swap_T_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_swap_T_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T11:43:54.186759Z","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":450,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_swap_blocks_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_swap_blocks_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T18:41:26.051769Z","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":443,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_swap_blocks_s0_layout2_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_swap_blocks_s0_layout2_20261008_v1.json"},{"created_at":"2026-10-09T07:03:29.797581Z","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":464,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_swap_blocks_s0_layout3_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_swap_blocks_s0_layout3_20261008_v1.json"},{"created_at":"2026-10-08T12:50:51.040798Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[3],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":762,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_sweep_blocks_random_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_sweep_blocks_random_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-08T12:36:18.946475Z","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[4],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":664,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_repeat_sweep_blocks_s0_layout1_20261008_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_repeat_sweep_blocks_s0_layout1_20261008_v1.json"},{"created_at":"2026-10-05T20:06:39.504097Z","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":264,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_solve_equation_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_solve_equation_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:07:57.795423Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":767,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_sort_nesting_dolls_by_size_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_sort_nesting_dolls_by_size_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:28:27.182495Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":662,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_sort_nesting_dolls_by_size_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_sort_nesting_dolls_by_size_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:12:23.993978Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_stack_blocks_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_stack_blocks_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T20:10:09.986755Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":246,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_stack_blocks_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_stack_blocks_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:07:36.549849Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":495,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_stack_bowls_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_stack_bowls_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:36:40.296345Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":458,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_stack_bowls_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_stack_bowls_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:25:43.911681Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":788,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_store_laptop_and_headphones_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_store_laptop_and_headphones_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:48:08.190862Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":772,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_store_laptop_and_headphones_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_store_laptop_and_headphones_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:45:16.583701Z","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":849,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_store_tools_in_toolbox_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_store_tools_in_toolbox_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-06T11:00:24.934535Z","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_swap_T_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_swap_T_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T22:16:07.416403Z","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":501,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_swap_blocks_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_swap_blocks_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:53:55.576386Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":737,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_sweep_blocks_random_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_sweep_blocks_random_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-05T21:54:18.542491Z","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":655,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_cap20_sweep_blocks_s0_layout0_20261006_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_cap20_sweep_blocks_s0_layout0_20261006_v1.json"},{"created_at":"2026-10-03T09:45:27.341866Z","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":88,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_v1_general_pickup_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:47:50.681003Z","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":263,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-cap20-medium-historical-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-15T18:07:36.078104+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"fbc192fd4fccb5278cfcdc526052b9a21a301a830834ec8bc79e446092ee1894","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"luna-medium-cap20-smoke-20261016","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-5.6-luna","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":60,"native_controls":622,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"luna-medium-cap20-smoke-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"luna-medium-cap20-smoke-20261016-a4-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/luna-medium-cap20-smoke-20261016-a4-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-11-02T14:54:17.142070+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-02T14:46:19.611742+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":5,"model_responses":5,"native_controls":103,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-02T14:52:20.477611+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":191,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-02T15:25:29.459859+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":931,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-11-02T14:59:59.389573+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":379,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:07:34.477268+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:12:00.816532+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":989,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-11-02T15:21:08.295796+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":1093,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-11-02T15:19:33.809634+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":1100,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:24:40.548928+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":1087,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-02T15:31:56.656034+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-02T15:48:55.135794+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":739,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:40:21.272458+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":800,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-02T15:40:47.561270+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":640,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:01:29.035480+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1199,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:01:08.274593+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":1750,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:00:14.392401+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":1295,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-11-02T15:55:41.131896+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":306,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-11-02T15:56:46.331184+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":348,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:50:50.834033+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":9,"model_responses":9,"native_controls":66,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-11-02T15:56:35.413877+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":133,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:08:29.860153+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":188,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:30:49.162297+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":1443,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:30:09.493218+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":1465,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:31:33.121265+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":1188,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:14:41.977436+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":457,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:22:32.754167+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":480,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:25:27.084809+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":582,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:55:52.216411+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1178,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-11-02T16:50:51.237652+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1198,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:33:10.396756+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":273,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:37:04.314998+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":335,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:40:34.647219+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":245,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:57:33.707478+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:52:48.410923+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":381,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-11-02T16:55:03.305033+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:57:05.353732+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":303,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-11-02T16:56:41.024376+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":324,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:03:22.497183+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":332,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-11-02T16:59:39.645915+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":3,"model_responses":3,"native_controls":160,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:11:20.567749+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":443,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:13:42.173748+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":538,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:10:42.354168+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":367,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:13:11.860468+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":441,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:16:36.642293+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":361,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:39:30.957759+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":330,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-push_T-random-s0-scene1.json"},{"created_at":"2026-11-02T17:35:16.459406+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":419,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-push_T-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:31:19.118932+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:27:21.039018+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:29:43.152583+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":698,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:24:28.568789+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":187,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:36:38.434075+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:33:09.926230+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":174,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:35:13.362303+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":10,"model_responses":10,"native_controls":139,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-11-02T17:49:06.362935+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":606,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:47:06.179006+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-02T17:53:10.120116+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":384,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-02T17:53:39.208326+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":313,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-02T17:57:36.794028+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":324,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-11-02T18:12:29.769753+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":800,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-11-02T18:00:33.660241+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":14,"model_responses":14,"native_controls":294,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-swap_T-standard-s0-scene1.json"},{"created_at":"2026-11-02T18:05:11.677112+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":400,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-swap_T-standard-s0-scene2.json"},{"created_at":"2026-11-02T18:10:11.834842+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"medium-nocap-dev63-20261102-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/medium-nocap-dev63-20261102-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-03T08:26:23.142407+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_align_blocks_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_align_blocks_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T12:56:13.922109+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":582,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_arrange_largest_number_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_arrange_largest_number_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T14:20:00.596890+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false},{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":853,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_arrange_largest_number_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_arrange_largest_number_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T04:29:54.546132+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":859,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_build_tower_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_build_tower_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T04:37:54.007140+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":1095,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_classify_objects_by_language_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_classify_objects_by_language_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T13:50:32.548098+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":1100,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_classify_objects_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_classify_objects_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T04:58:06.234493+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":478,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_cover_blocks_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_cover_blocks_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T08:26:02.018167+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":263,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_deposit_coin_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_deposit_coin_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:02:16.255149+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":1243,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_fasten_screws_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_fasten_screws_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:44:43.240733+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":91,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_fill_egg_holder_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_fill_egg_holder_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T17:49:29.034770+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":991,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_fill_pen_holder_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_fill_pen_holder_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T08:54:28.561963+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_fold_clothes_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_fold_clothes_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T09:10:06.617270+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false},{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":385,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_fold_clothes_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_fold_clothes_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T09:45:27.341866+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":88,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_general_pickup_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T17:54:20.031060+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":728,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_hang_mugs_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_hang_mugs_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:52:02.483902+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":707,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_hang_mugs_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_hang_mugs_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T05:20:15.077019+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":1411,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_imitate_sorting_sequence_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_imitate_sorting_sequence_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T09:45:31.846077+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":197,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_insert_key_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_insert_key_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T05:21:15.740296+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_insert_tubes_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_insert_tubes_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:43:54.643525+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":515,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_make_kong_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_make_kong_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:25:42.602378+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":808,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_make_toast_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_make_toast_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:01:17.595926+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":529,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_make_toast_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_make_toast_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T13:36:11.533426+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":491,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_match_and_pick_from_conveyor_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_match_and_pick_from_conveyor_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T06:00:57.717679+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":997,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_organize_table_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_organize_table_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:43:44.639277+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1077,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_pack_objects_into_box_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_pack_objects_into_box_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:35:58.119790+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false},{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":1189,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_pack_objects_into_box_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_pack_objects_into_box_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T11:43:23.486264+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":257,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_pick_from_conveyor_by_image_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_pick_from_conveyor_by_image_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:11:56.409086+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":428,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_play_Xylophone_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_play_Xylophone_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:02:01.787148+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":669,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_play_stacking_toy_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_play_stacking_toy_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T17:59:54.202591+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":507,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_play_tic_tac_toe_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_play_tic_tac_toe_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T13:39:32.902181+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":392,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_plug_in_charger_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_plug_in_charger_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T14:14:15.973286+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":360,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_pour_balls_into_vase_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_pour_balls_into_vase_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T17:54:23.131294+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_pour_by_language_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_pour_by_language_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T15:20:57.958148+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":358,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_pour_liquid_into_cup_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_pour_liquid_into_cup_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T13:29:54.935144+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":258,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_pour_liquid_into_cup_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_pour_liquid_into_cup_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:33:21.965680+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":348,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_press_by_number_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_press_by_number_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T05:50:49.582847+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":251,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_push_T_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_push_T_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:44:48.095844+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false},{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":303,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_push_T_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_push_T_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T06:22:17.463832+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_put_bottles_into_dustbin_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_put_bottles_into_dustbin_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T06:09:58.356102+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":219,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_solve_equation_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_solve_equation_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:50:14.293736+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":1004,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:49:48.783218+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false},{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":941,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:47:50.681003+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":263,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:35:49.055254+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":467,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_stack_blocks_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_stack_blocks_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:26:10.981244+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":381,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_stack_blocks_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_stack_blocks_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T17:47:38.013208+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":484,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_stack_bowls_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_stack_bowls_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-02T06:25:29.413463+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false},{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":388,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_stack_bowls_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_stack_bowls_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:34:31.217307+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":671,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_store_laptop_and_headphones_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_store_laptop_and_headphones_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:33:38.564407+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":726,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_store_laptop_and_headphones_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_store_laptop_and_headphones_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:31:53.463619+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":807,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_store_tools_in_toolbox_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_store_tools_in_toolbox_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T18:46:28.132127+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_swap_T_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_swap_T_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:39:46.688232+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":631,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_swap_blocks_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_swap_blocks_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:59:23.471098+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":694,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_sweep_blocks_random_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_sweep_blocks_random_s0_layout0_20261002_v1.json"},{"created_at":"2026-10-03T19:57:27.002042+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","preserved_unselected":true,"rounds":[],"selected":false,"selection_id":"persistent-nocap-medium-mixed42-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":895,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"persistent-nocap-medium-historical-v1","max_decisions":100,"native_control_cap":null,"profile":"persistent-nocap","score_scale":"0..1"},"run_id":"nocap-import-l3_persistent_v1_sweep_blocks_s0_layout0_20261002_v1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/nocap-import-l3_persistent_v1_sweep_blocks_s0_layout0_20261002_v1.json"},{"created_at":"2026-11-02T05:43:57.793204+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":72,"native_controls":409,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-depth-pilot-20261102-131035-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-depth-pilot-20261102-131035-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-11-03T10:47:07.171119+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":45,"native_controls":175,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:21:56.808561+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":null,"native_controls":692,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-11-03T10:20:41.309810+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":null,"native_controls":735,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-build_tower-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:31:27.529471+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":96,"native_controls":892,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-11-03T11:40:16.175907+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":107,"native_controls":729,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:54:11.347318+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":72,"native_controls":401,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:22:11.118865+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":null,"native_controls":679,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-11-03T11:39:29.018262+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":112,"native_controls":460,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:26:03.508671+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":109,"native_controls":933,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-11-03T09:47:50.337623+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":null,"native_controls":493,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-11-03T10:42:17.489375+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":12,"native_controls":69,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:20:08.203240+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":745,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-11-03T12:51:21.898072+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":83,"native_controls":987,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-11-03T12:46:43.868405+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":104,"native_controls":466,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-make_kong-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:58:08.453562+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":684,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-make_toast-random-s0-scene0.json"},{"created_at":"2026-11-03T10:39:31.181780+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":41,"native_controls":362,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:54:14.083000+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":96,"native_controls":616,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-organize_table-standard-s0-scene0.json"},{"created_at":"2026-11-03T09:53:16.019644+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":null,"native_controls":936,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-11-03T11:08:08.665831+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":60,"native_controls":510,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:13:01.639452+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":null,"native_controls":392,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-11-03T11:29:38.687614+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":112,"native_controls":562,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-11-03T11:24:42.147655+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":101,"native_controls":422,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-11-03T09:22:40.408368+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":null,"native_controls":321,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-11-03T11:29:54.017876+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":76,"native_controls":686,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-11-03T09:24:04.705232+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":null,"native_controls":364,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-11-03T10:42:38.645264+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":40,"native_controls":309,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-11-03T09:51:13.574954+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":59,"native_controls":328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-push_T-random-s0-scene0.json"},{"created_at":"2026-11-03T09:45:17.839110+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":null,"native_controls":659,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:55:06.354504+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":31,"native_controls":248,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-11-03T11:17:26.265327+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":null,"native_controls":1001,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-11-03T10:58:48.510398+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":58,"native_controls":330,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:14:09.185433+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":null,"native_controls":476,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-11-03T09:56:09.586395+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":null,"native_controls":545,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-11-03T11:56:38.505820+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":109,"native_controls":806,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:46:12.901184+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":41,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-swap_T-standard-s0-scene0.json"},{"created_at":"2026-11-03T10:12:04.997293+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":719,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-round1-restart-20261103-154255-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-round1-restart-20261103-154255-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-11-04T07:52:47.167796+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":51,"native_controls":403,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-gt-swap-restart-20261103-230600-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-gt-swap-restart-20261103-230600-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-02T08:43:15.340835+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":40,"native_controls":290,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-precision4-20261102-135343-coinfix2-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-precision4-20261102-135343-coinfix2-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-11-02T06:48:44.098182+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":31,"native_controls":233,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-precision4-20261102-135343-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-precision4-20261102-135343-insert_key-standard-s0-scene0.json"},{"created_at":"2026-11-02T08:29:37.407026+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":null,"native_controls":500,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-precision4-20261102-135343-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-precision4-20261102-135343-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-11-02T07:59:14.732388+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-coding-gt-mixed42-round1-20261104","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":49,"native_controls":310,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-coding-gt-mixed42-round1-20261104","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23-coding-gt-depth","score_scale":"0..1"},"run_id":"o23-coding-precision4-20261102-135343-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-coding-precision4-20261102-135343-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-11-04T12:16:13.904202+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":46,"native_controls":148,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-04T12:10:48.446361+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":40,"native_controls":175,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-04T13:19:08.328221+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":31,"native_controls":127,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-04T20:49:33.250624+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":114,"model_responses":null,"native_controls":697,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-11-04T19:07:25.862329+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":130,"model_responses":132,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-11-04T18:49:31.488629+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":123,"model_responses":125,"native_controls":1089,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-11-04T17:56:36.536087+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":107,"model_responses":109,"native_controls":1016,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-11-04T18:55:27.670394+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":122,"model_responses":125,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-04T19:46:50.080644+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":164,"model_responses":167,"native_controls":1096,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-05T06:10:12.987534+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":295,"model_responses":null,"native_controls":1698,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-11-04T20:48:11.769608+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":163,"model_responses":null,"native_controls":1368,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-11-04T10:36:54.668580+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":null,"native_controls":226,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-11-04T17:44:34.241199+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":59,"native_controls":489,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-11-04T14:56:53.345911+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":36,"native_controls":298,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-11-04T17:36:33.294050+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":11,"native_controls":62,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-11-04T17:47:36.991079+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":18,"model_responses":18,"native_controls":101,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-11-04T17:49:17.726624+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":86,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-11-04T19:21:49.577671+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":120,"model_responses":122,"native_controls":1358,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-11-04T10:21:38.863883+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":442,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-11-04T10:26:08.513390+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":321,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-11-04T10:21:27.789511+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":31,"native_controls":310,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-11-04T21:08:00.809408+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":133,"model_responses":181,"native_controls":1212,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-11-04T19:15:07.734219+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":140,"model_responses":null,"native_controls":1290,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-11-04T09:34:25.538941+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":40,"native_controls":392,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-11-04T08:57:31.801873+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":42,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-11-04T14:50:45.818081+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":null,"native_controls":616,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-11-05T01:55:28.750296+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":null,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-11-04T13:55:52.726476+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":74,"native_controls":399,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-11-04T10:32:46.059509+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-11-04T08:59:34.247549+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":329,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-11-05T02:04:14.443201+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":58,"native_controls":485,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-11-05T01:24:44.945710+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":28,"native_controls":332,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-11-05T01:28:31.676887+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":36,"native_controls":331,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-11-04T16:48:35.688930+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":25,"native_controls":168,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-11-04T17:47:19.954643+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":42,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-11-04T17:35:57.510013+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":29,"native_controls":183,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-11-04T18:30:53.118594+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":111,"model_responses":null,"native_controls":1050,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-11-04T18:41:18.218436+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":117,"model_responses":null,"native_controls":775,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-11-04T08:44:50.595474+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":34,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev39-rerun-20261104-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev39-rerun-20261104-swap_T-standard-s0-scene3.json"},{"created_at":"2026-11-03T16:21:44.958347+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":131,"model_responses":134,"native_controls":718,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-11-03T15:33:03.618365+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":65,"native_controls":465,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-11-03T16:20:58.826059+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":127,"model_responses":130,"native_controls":1100,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-04T04:36:05.285431+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":61,"native_controls":408,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-04T04:41:56.864120+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":71,"native_controls":422,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-04T04:41:55.425588+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":64,"native_controls":406,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-03T16:38:04.508306+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":123,"model_responses":125,"native_controls":1595,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-11-03T16:33:51.951603+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":116,"model_responses":118,"native_controls":1365,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-11-03T16:15:46.269484+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":115,"model_responses":119,"native_controls":1146,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-11-04T05:05:01.285201+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":97,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-11-04T05:17:46.078033+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":102,"model_responses":104,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-11-04T04:48:01.692672+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":66,"native_controls":521,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-11-04T04:26:16.359544+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":40,"native_controls":346,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-11-04T04:26:16.966810+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":31,"native_controls":270,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-11-04T05:15:17.142702+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":377,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-11-04T05:15:03.495110+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":79,"native_controls":257,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-push_T-random-s0-scene1.json"},{"created_at":"2026-11-04T05:20:16.077788+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":90,"native_controls":306,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene0.json"},{"created_at":"2026-11-04T05:25:52.977304+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":104,"native_controls":240,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene1.json"},{"created_at":"2026-11-04T05:28:02.724663+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":114,"model_responses":119,"native_controls":697,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-11-04T04:44:43.637835+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":67,"native_controls":650,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-11-04T04:48:08.276108+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":72,"native_controls":700,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-11-03T15:59:48.823291+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":113,"model_responses":116,"native_controls":723,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-11-03T16:22:17.596353+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":138,"model_responses":142,"native_controls":972,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-11-04T05:06:29.635620+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":49,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-04T05:03:55.108312+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":47,"native_controls":393,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-04T05:04:48.924452+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":45,"native_controls":327,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-04T05:30:39.998299+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":104,"model_responses":110,"native_controls":740,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-11-04T05:00:50.017390+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":91,"native_controls":544,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-11-04T05:06:47.990650+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":50,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene1.json"},{"created_at":"2026-11-04T05:09:21.280087+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":51,"native_controls":380,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-dev69-20261102","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-30T12:15:47.377090+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-eight-20261030","supplementary":false},{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":129,"model_responses":null,"native_controls":938,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-eight-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-30T10:07:17.970442+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-eight-20261030","supplementary":false},{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":91,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-eight-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-30T13:36:17.460551+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-eight-20261030","supplementary":false},{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":129,"model_responses":null,"native_controls":1094,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-eight-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-30T12:56:07.896645+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-eight-20261030","supplementary":false},{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":110,"model_responses":null,"native_controls":685,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-eight-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-30T09:34:30.595268+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-eight-20261030","supplementary":false},{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":62,"native_controls":496,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-eight-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-11-01T12:04:16.811196+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-eight-20261030","supplementary":false},{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":271,"model_responses":293,"native_controls":1400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-eight-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0.json"},{"created_at":"2026-11-01T06:36:12.712085+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-eight-20261030","supplementary":false},{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":176,"model_responses":null,"native_controls":1141,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-eight-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-30T14:12:33.299745+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-eight-20261030","supplementary":false},{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":136,"model_responses":null,"native_controls":800,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-eight-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-30T15:52:17.326508+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":33,"native_controls":149,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-01T11:26:15.484725+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":138,"model_responses":141,"native_controls":702,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-30T16:03:29.304687+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":87,"native_controls":887,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-11-01T07:25:22.815544+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":121,"model_responses":122,"native_controls":1044,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-11-01T06:14:36.243869+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":75,"native_controls":500,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-30T15:32:16.267900+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":37,"native_controls":278,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-11-01T14:53:55.866244+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":232,"model_responses":240,"native_controls":1551,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-30T16:10:52.633881+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":33,"native_controls":267,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-30T15:59:25.754759+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":72,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-11-01T11:23:44.349668+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":137,"model_responses":139,"native_controls":1600,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-30T15:11:13.757455+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":192,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0.json"},{"created_at":"2026-11-01T06:51:11.472007+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":131,"model_responses":null,"native_controls":540,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-30T16:28:10.803049+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":37,"native_controls":420,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-11-01T13:32:21.394002+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":188,"model_responses":195,"native_controls":936,"native_terminal":true,"score":0.75,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0.json"},{"created_at":"2026-11-01T08:25:13.821896+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":141,"model_responses":144,"native_controls":1300,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-11-01T06:29:29.867325+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":82,"native_controls":635,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-30T16:39:52.552583+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":64,"native_controls":318,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-11-01T22:22:17.719487+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":508,"model_responses":null,"native_controls":1068,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-30T15:03:19.756927+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":37,"native_controls":276,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-30T16:46:00.499649+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":78,"native_controls":588,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-30T15:46:29.019704+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":65,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-30T15:27:18.009577+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":35,"native_controls":344,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-11-01T06:36:50.343494+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-11-01T06:34:21.035374+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":58,"native_controls":302,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0.json"},{"created_at":"2026-10-30T16:43:18.340129+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":69,"native_controls":690,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-11-01T07:07:57.091980+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":32,"native_controls":243,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-11-01T11:53:36.611680+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":144,"model_responses":null,"native_controls":1050,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-11-01T06:51:56.378460+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":47,"native_controls":332,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-11-01T07:14:32.024630+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":52,"native_controls":357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-11-01T08:32:41.689521+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":56,"native_controls":413,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-30T16:46:49.022246+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":109,"model_responses":117,"native_controls":877,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-11-01T08:15:28.137117+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":45,"native_controls":362,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-30T15:40:05.294665+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":393,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-01T11:24:32.118159+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-first42-20261030","supplementary":false},{"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-devset-111","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":161,"model_responses":164,"native_controls":862,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-first42-add34-20261030","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-11-04T13:56:48.940518+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"04125cdc21c749943effdd733bed1fecce9d72e3e35a537a921956b3dcea0144","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-fixprompt","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":300,"model_responses":null,"native_controls":1870,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-fixprompt","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-fixprompt-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-fixprompt-20261102-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-fixprompt-20261102-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-11-02T22:34:13.781495+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"04125cdc21c749943effdd733bed1fecce9d72e3e35a537a921956b3dcea0144","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-fixprompt","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":145,"model_responses":null,"native_controls":1300,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-fixprompt","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-fixprompt-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-fixprompt-20261102-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-fixprompt-20261102-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-11-02T11:04:35.543911+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"04125cdc21c749943effdd733bed1fecce9d72e3e35a537a921956b3dcea0144","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-fixprompt","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":84,"native_controls":435,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-fixprompt","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-fixprompt-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-fixprompt-20261102-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-fixprompt-20261102-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-11-02T10:11:57.957982+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"04125cdc21c749943effdd733bed1fecce9d72e3e35a537a921956b3dcea0144","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-fixprompt","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":32,"native_controls":385,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-coding-unlimited-fixprompt","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-fixprompt-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-fixprompt-20261102-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-fixprompt-20261102-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-11-02T10:43:05.489494+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"04125cdc21c749943effdd733bed1fecce9d72e3e35a537a921956b3dcea0144","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-coding-unlimited-fixprompt","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":65,"native_controls":387,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-coding-unlimited-fixprompt","max_decisions":null,"native_control_cap":20,"profile":"o23-depthpro-coding-unlimited-fixprompt-v1","score_scale":"0..1"},"run_id":"o23-depthpro-coding-unlimited-fixprompt-20261102-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-coding-unlimited-fixprompt-20261102-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-05T05:37:06.715056+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":120,"model_responses":121,"native_controls":590,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-11-05T06:37:45.094549+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":123,"model_responses":125,"native_controls":813,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-build_tower-standard-s0-scene0.json"},{"created_at":"2026-11-05T13:24:16.736015+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":70,"native_controls":847,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-11-04T18:26:12.256458+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":467,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-05T03:51:17.171679+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":281,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-11-05T12:17:01.893430+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":150,"model_responses":152,"native_controls":1100,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-11-04T17:15:12.100115+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":466,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-11-05T08:46:04.782832+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":10,"model_responses":10,"native_controls":68,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-11-04T18:10:56.888586+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":123,"model_responses":124,"native_controls":800,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-11-05T13:37:15.729388+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":104,"model_responses":106,"native_controls":1369,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-11-04T18:28:09.109504+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":261,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_key-standard-s0-scene0.json"},{"created_at":"2026-11-04T17:49:13.689304+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":481,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-11-05T13:48:40.741201+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":137,"model_responses":139,"native_controls":600,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_kong-standard-s0-scene0.json"},{"created_at":"2026-11-05T05:22:39.263727+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":189,"model_responses":192,"native_controls":1328,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_toast-random-s0-scene0.json"},{"created_at":"2026-11-05T07:54:22.817826+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":333,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-11-05T08:46:02.551605+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":180,"model_responses":182,"native_controls":956,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-organize_table-standard-s0-scene0.json"},{"created_at":"2026-11-05T03:26:50.251682+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":154,"model_responses":156,"native_controls":1184,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-11-05T06:09:46.678096+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":85,"native_controls":464,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-11-05T06:12:52.996561+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":197,"model_responses":200,"native_controls":1200,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-11-04T17:34:46.383392+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":303,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-11-05T04:55:06.002299+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":512,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-11-05T15:24:01.271917+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":800,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-11-05T02:52:30.479584+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-11-04T18:33:56.357522+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":5,"model_responses":5,"native_controls":51,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-11-05T06:26:23.490133+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":144,"model_responses":146,"native_controls":509,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-push_T-random-s0-scene0.json"},{"created_at":"2026-11-05T07:19:02.956171+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":82,"native_controls":700,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-11-05T13:31:40.443791+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":279,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-11-04T17:49:41.305623+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":107,"model_responses":108,"native_controls":786,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-11-04T17:10:31.208333+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":360,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-11-04T17:17:09.116542+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":73,"native_controls":589,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-11-05T03:57:48.944858+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":440,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-11-05T08:19:31.825052+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":394,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_T-standard-s0-scene0.json"},{"created_at":"2026-11-05T08:54:51.730366+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":402,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-11-04T17:01:30.764277+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23-depthpro-unlimited","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":310,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23-depthpro-unlimited","max_decisions":null,"native_control_cap":20,"profile":"persistent-cap20-o23-depthpro","score_scale":"0..1"},"run_id":"o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-28T19:51:34.842561+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":141,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-28T19:51:11.977652+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-28T19:43:57.498669+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":134,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-29T03:31:42.973058+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":null,"native_controls":642,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-29T03:28:12.653574+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":null,"native_controls":586,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-28T20:13:27.327871+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":324,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-29T04:43:51.435411+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":null,"native_controls":895,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-29T03:24:07.456661+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":null,"native_controls":1031,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-29T03:42:51.268014+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":894,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-29T03:39:41.830941+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":1067,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-29T03:44:04.758440+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":991,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-29T03:40:09.481573+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":null,"native_controls":993,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-29T02:03:44.072733+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":null,"native_controls":415,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-29T03:15:01.404124+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":null,"native_controls":404,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-29T02:21:18.876292+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":null,"native_controls":416,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-29T03:48:01.297976+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":1071,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-29T04:11:35.609022+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":null,"native_controls":1086,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-29T02:11:30.161903+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":null,"native_controls":401,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-29T03:21:02.631022+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":284,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-29T04:35:37.433619+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":null,"native_controls":435,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-29T03:10:51.296323+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":336,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-29T02:35:02.855089+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":10,"model_responses":10,"native_controls":61,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-29T03:30:57.721378+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":175,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-29T03:25:49.772002+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":77,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-29T09:13:41.037324+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":97,"native_controls":1392,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-29T11:48:21.174350+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1363,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-29T08:53:27.710865+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":null,"native_controls":1404,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-28T19:49:06.754935+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":357,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-28T19:38:44.745601+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":260,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-28T20:15:50.968239+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":326,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-29T08:43:19.975242+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1065,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-29T06:09:07.308155+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":993,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-29T05:36:45.530230+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":641,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-28T20:34:53.424712+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":445,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-29T03:29:17.297486+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":null,"native_controls":632,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-29T02:02:44.331464+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":null,"native_controls":240,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-29T06:04:10.336990+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":86,"native_controls":491,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-29T05:49:29.400794+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":331,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-29T06:05:37.245706+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":386,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-29T06:10:01.949008+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":348,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-29T12:27:03.607135+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":69,"native_controls":392,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-29T08:09:13.790180+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":null,"native_controls":371,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-29T07:52:39.462218+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":245,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-29T08:55:51.152981+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":439,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-29T12:07:14.554483+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":414,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-29T03:06:40.370412+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":null,"native_controls":369,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-30T03:24:30.678232+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":null,"native_controls":312,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-push_T-random-s0-scene1.json"},{"created_at":"2026-10-29T14:39:30.686108+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":null,"native_controls":239,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-30T03:50:19.669672+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":null,"native_controls":254,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-29T05:40:48.714211+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-29T05:41:39.160395+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":76,"native_controls":653,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-29T05:29:41.589586+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":678,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-29T11:55:27.778405+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":203,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-29T12:28:26.678177+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":284,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-29T11:48:35.215170+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":191,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-29T06:25:49.523221+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":88,"native_controls":888,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-29T05:58:02.717982+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":84,"native_controls":755,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-29T04:45:43.845891+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":330,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-29T14:39:12.016684+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-29T14:35:20.737911+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":307,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-30T04:00:56.729734+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":null,"native_controls":336,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-30T05:41:16.988574+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":null,"native_controls":691,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-29T14:57:42.212533+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":403,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-30T06:03:32.012981+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":null,"native_controls":462,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-29T14:43:33.240514+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-30T03:47:32.689043+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":null,"native_controls":309,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-30T03:39:27.326851+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":null,"native_controls":393,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-20261029-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-20261029-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-30T06:47:07.549680+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":88,"native_controls":341,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-rerun-20261030-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-rerun-20261030-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-30T05:04:22.506138+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[2],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":56,"native_controls":307,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-dev69-rerun-20261030-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-dev69-rerun-20261030-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-28T17:52:06.722753+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":174,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-28T15:09:13.154002+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":null,"native_controls":640,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-28T16:56:48.948672+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":808,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-28T15:34:05.075054+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":null,"native_controls":1000,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-28T15:24:48.364265+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":null,"native_controls":933,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-28T19:30:54.320843+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":77,"native_controls":396,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-28T11:59:08.257517+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":286,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-28T18:52:41.306757+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":null,"native_controls":739,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-28T16:51:34.170048+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":409,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-28T11:52:20.188324+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":313,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-28T13:24:04.623605+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":493,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-28T17:47:20.592136+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":75,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-28T19:42:17.441076+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":null,"native_controls":674,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-28T17:58:57.966808+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":1230,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-28T11:32:57.663695+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":283,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-28T13:41:37.644313+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":null,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-28T15:49:06.730013+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":null,"native_controls":385,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-28T18:03:41.456776+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":null,"native_controls":708,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-28T15:58:50.173427+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-28T16:15:20.125598+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":null,"native_controls":656,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-28T14:49:19.010752+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":89,"native_controls":916,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-28T17:00:18.607688+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":473,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-28T16:37:02.520883+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":null,"native_controls":355,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-28T16:16:45.894609+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":null,"native_controls":656,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-28T16:55:10.113656+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":274,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-28T12:25:51.330244+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":331,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-28T11:41:13.389951+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":309,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-28T17:43:21.834837+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":728,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-28T15:25:23.557586+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":335,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-28T11:55:42.327938+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":312,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-28T17:22:16.754424+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":null,"native_controls":166,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-push_T-random-s0-scene0.json"},{"created_at":"2026-10-28T13:14:27.832098+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-28T18:54:47.190458+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":271,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-28T16:17:46.355267+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":null,"native_controls":674,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-28T17:36:49.435767+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":null,"native_controls":399,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-28T18:59:12.834702+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":387,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-28T18:04:05.483822+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":null,"native_controls":444,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-28T19:43:10.311159+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":720,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-29T02:12:16.034590+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":null,"native_controls":734,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-28T14:02:55.029974+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":391,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-28T18:53:01.102120+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":405,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-28T16:32:39.218647+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":null,"native_controls":593,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-20261028-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-20261028-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-30T09:39:30.554862+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-first42-eight-sim-rerun-20261030","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":737,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-compact-first42-eight-sim-rerun-20261030","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-eight-sim-rerun-20261030-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-eight-sim-rerun-20261030-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-30T08:58:00.329908+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-first42-eight-sim-rerun-20261030","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":null,"native_controls":574,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-first42-eight-sim-rerun-20261030","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-eight-sim-rerun-20261030-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-eight-sim-rerun-20261030-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-30T08:55:01.374300+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-first42-eight-sim-rerun-20261030","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":798,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-first42-eight-sim-rerun-20261030","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-eight-sim-rerun-20261030-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-eight-sim-rerun-20261030-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-30T08:36:37.987767+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-first42-eight-sim-rerun-20261030","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":null,"native_controls":576,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-first42-eight-sim-rerun-20261030","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-eight-sim-rerun-20261030-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-eight-sim-rerun-20261030-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-30T07:19:16.522097+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-first42-eight-sim-rerun-20261030","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":489,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-compact-first42-eight-sim-rerun-20261030","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-eight-sim-rerun-20261030-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-eight-sim-rerun-20261030-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-30T09:29:38.778402+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-first42-eight-sim-rerun-20261030","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":767,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-first42-eight-sim-rerun-20261030","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-eight-sim-rerun-20261030-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-eight-sim-rerun-20261030-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-30T09:43:24.678087+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-first42-eight-sim-rerun-20261030","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":710,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"o23456-compact-first42-eight-sim-rerun-20261030","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-eight-sim-rerun-20261030-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-eight-sim-rerun-20261030-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-30T06:33:28.101858+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-compact-first42-eight-sim-rerun-20261030","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":267,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-compact-first42-eight-sim-rerun-20261030","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-compact","score_scale":"0..1"},"run_id":"o23456-compact-first42-eight-sim-rerun-20261030-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-compact-first42-eight-sim-rerun-20261030-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-27T18:38:11.823409+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":150,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-27T14:44:00.917568+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":72,"native_controls":612,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-27T17:33:05.313109+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":912,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-28T04:03:52.791319+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":1021,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-27T19:23:49.297079+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":80,"native_controls":512,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-27T14:22:00.874641+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":257,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-27T13:29:25.406065+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":308,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:08:52.931774+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":87,"native_controls":687,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:42:29.060773+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":96,"native_controls":965,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-27T12:32:47.521747+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":361,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-27T16:16:05.760414+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":64,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-27T19:28:07.299611+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1491,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-27T16:26:46.251993+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":300,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-27T16:29:43.944242+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":408,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-28T03:14:36.302331+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":null,"native_controls":476,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-27T16:23:12.354786+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":97,"native_controls":620,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-27T14:27:52.841318+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":443,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:26:48.357582+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":814,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-27T12:11:21.034898+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":331,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-27T16:42:10.046989+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":258,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-27T17:17:14.825162+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":88,"native_controls":496,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-27T19:50:52.854295+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":99,"native_controls":613,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-27T16:09:50.878494+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":97,"native_controls":234,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-27T12:50:06.261351+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":390,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:57:02.914085+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":116,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-28T03:27:20.893429+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":null,"native_controls":597,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-27T12:08:05.863501+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":326,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-27T16:25:24.913995+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":320,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:35:08.845099+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":70,"native_controls":175,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-push_T-random-s0-scene0.json"},{"created_at":"2026-10-27T14:42:09.538691+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:37:20.576336+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":270,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-27T13:24:16.907470+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":605,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-27T13:50:25.952081+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":481,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-27T18:23:29.412933+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":275,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-27T14:01:07.761217+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":563,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-27T15:09:21.252449+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":606,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-28T05:17:46.048900+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":null,"native_controls":751,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:10:39.709459+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-27T17:15:48.767349+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":513,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:08:54.143963+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":83,"native_controls":604,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-27T10:53:22.670999+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":null,"native_controls":981,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-27T09:17:26.175332+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":391,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-26T03:02:57.443737+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":null,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-26T08:39:24.184432+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":631,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-25T20:46:28.836997+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":331,"native_controls":989,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-26T08:08:31.952498+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":null,"native_controls":499,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-26T08:09:16.484912+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":542,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-26T08:55:30.350477+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":408,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-26T08:56:29.604245+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":720,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-26T07:06:28.880056+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":null,"native_controls":339,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-25T14:44:55.537881+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":16,"native_controls":119,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-26T03:02:41.958971+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":null,"native_controls":249,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-26T06:43:44.005324+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":null,"native_controls":446,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-26T09:31:27.499595+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":null,"native_controls":351,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-26T08:17:49.291692+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":null,"native_controls":638,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-26T06:26:43.857285+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":775,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-26T08:02:09.195123+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":null,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-26T06:35:55.667780+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":862,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-26T06:55:33.563643+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":null,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-26T07:10:51.492419+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":null,"native_controls":443,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-26T06:44:30.737739+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":null,"native_controls":346,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-25T19:15:15.452725+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":162,"native_controls":700,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-26T09:57:56.497711+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":37,"native_controls":265,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-26T08:59:47.501046+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":812,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-25T18:50:43.713056+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":108,"native_controls":550,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-26T08:42:46.297476+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":704,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-26T06:57:05.518899+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":null,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-26T08:37:33.425767+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1-init2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":421,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1-init2","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-init2-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-init2-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-27T06:33:44.152894+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":46,"native_controls":454,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab1-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab1-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-27T06:18:52.425662+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":319,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-27T06:46:04.806584+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":334,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-27T07:02:19.109784+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":490,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-27T10:24:17.929146+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":369,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-27T10:27:58.666270+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":324,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-27T15:26:59.129868+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":529,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-27T18:27:46.937309+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":97,"native_controls":657,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-27T21:49:39.053263+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":98,"native_controls":1009,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-27T21:58:15.345191+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1048,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-27T19:30:51.174021+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":979,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-27T19:20:48.639079+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":78,"native_controls":521,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-27T20:04:31.124799+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":575,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-27T16:37:26.637961+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":973,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-27T13:47:01.154989+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":449,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-27T15:11:17.262451+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":573,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-27T18:32:59.007827+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":366,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-27T16:15:43.841987+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":95,"native_controls":237,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-push_T-random-s0-scene1.json"},{"created_at":"2026-10-27T15:32:56.961319+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":99,"native_controls":330,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-27T17:54:19.075667+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":508,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-27T20:23:47.098694+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":674,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-27T20:46:04.220032+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":209,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-27T21:00:14.205154+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-27T21:13:53.848267+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":235,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-27T16:17:11.793029+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":313,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-27T16:47:48.949583+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":546,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-27T17:56:15.411917+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":518,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-27T15:44:00.408461+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":676,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-27T13:20:50.472546+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":380,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-27T13:41:34.865988+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":420,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-27T20:10:01.449478+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-27T20:40:06.774236+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":332,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-27T20:35:08.089035+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-27T23:30:17.810635+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":76,"native_controls":586,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab5-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab5-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-28T00:11:38.842853+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":92,"native_controls":1085,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab5-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab5-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-27T23:17:28.946681+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-6fig-cuda-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":674,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-6fig-cuda-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro-6fig-cuda","score_scale":"0..1"},"run_id":"o23456-depthpro-6fig-cuda-v1-stab5-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-6fig-cuda-v1-stab5-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-24T07:52:57.516306+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-24T18:01:20.945705+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":null,"native_controls":884,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-24T17:33:38.610099+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":null,"native_controls":606,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-24T05:51:17.308256+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":139,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-24T22:17:42.576704+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":1227,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-24T18:43:14.961970+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":436,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-24T07:20:20.179358+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":437,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-24T14:28:56.276279+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":null,"native_controls":353,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-24T11:59:49.091914+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":null,"native_controls":516,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-24T18:39:36.690029+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":null,"native_controls":514,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-24T12:17:40.703676+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":null,"native_controls":696,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-24T07:39:00.777062+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":306,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-24T06:52:08.071800+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":220,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-24T12:36:22.571636+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":null,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-24T18:37:38.509039+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":null,"native_controls":899,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-24T07:41:48.120716+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-24T12:32:57.242342+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"o23456-depthpro-cap20-20261024","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":null,"native_controls":404,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"o23456-depthpro-cap20-20261024","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-depthpro","score_scale":"0..1"},"run_id":"o23456-depthpro-cap20-20261024-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/o23456-depthpro-cap20-20261024-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-30T14:53:28.539259+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-00-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-00-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-31T21:24:17.943310+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":null,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-01-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-01-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-31T08:30:27.082562+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-02-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-02-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-31T10:42:20.905294+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":null,"native_controls":502,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-03-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-03-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-11-01T05:18:35.886846+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":null,"native_controls":622,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-04-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-04-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-11-01T05:17:52.571299+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":null,"native_controls":421,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-05-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-05-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:46:11.598870+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":null,"native_controls":982,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-06-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-06-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:51:55.030661+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":null,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-07-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-07-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-11-01T05:28:02.432385+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":null,"native_controls":1096,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-08-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-08-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-11-01T05:35:51.758529+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":null,"native_controls":1058,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:34:52.184851+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":null,"native_controls":1087,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-10-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-10-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-01T05:43:16.948473+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":null,"native_controls":989,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-11-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-11-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-01T05:46:52.446044+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":737,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-12-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-12-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:44:43.703751+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":null,"native_controls":800,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-13-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-13-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-01T05:16:18.995106+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":null,"native_controls":518,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-14-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-14-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-01T05:49:22.533054+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":955,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-15-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-15-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:46:20.756039+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":null,"native_controls":1101,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-16-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-16-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-11-01T05:50:34.164545+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":null,"native_controls":1054,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-17-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-17-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-11-01T05:07:13.854065+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":null,"native_controls":369,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-18-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-18-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-11-01T05:17:01.366951+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":null,"native_controls":374,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-19-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-19-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-11-01T05:36:52.990206+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":369,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-20-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-20-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:26:06.901392+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":19,"model_responses":19,"native_controls":124,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-21-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-21-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:53:33.290205+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":14,"model_responses":14,"native_controls":130,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-22-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-22-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:03:46.883440+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-23-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-23-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:23:11.441932+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1468,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:23:30.010933+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1593,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-25-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-25-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:04:46.602134+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":1231,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-26-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-26-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-11-01T05:58:58.676488+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":435,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:05:08.714660+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":379,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-28-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-28-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:03:18.945891+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":474,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-29-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-29-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:00:52.656273+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1190,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-11-01T06:32:30.561645+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1008,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-31-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-31-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-11-01T06:25:13.541279+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":1153,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-32-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-32-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:01:53.342551+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":263,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:25:17.430028+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":442,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-34-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-34-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-11-01T05:28:28.180122+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":267,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-35-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-35-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-11-01T05:58:59.684066+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":319,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-36-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-36-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:56:29.702216+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-37-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-37-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:21:14.152433+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":467,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-38-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-38-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:25:17.371379+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":342,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-39-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-39-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:34:51.983190+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":349,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-40-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-40-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:36:52.444790+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":350,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-41-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-41-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:19:02.685122+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":324,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:09:34.254940+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":259,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-43-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-43-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:12:39.267051+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":159,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-44-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-44-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:20:35.897367+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":398,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-45-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-45-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:15:22.677473+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":363,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-46-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-46-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:46:58.377048+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":358,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-47-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-47-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:49:31.524751+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":328,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-48-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-48-push_T-standard-s0-scene0.json"},{"created_at":"2026-11-01T06:43:42.458446+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":309,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-49-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-49-push_T-random-s0-scene1.json"},{"created_at":"2026-11-01T05:58:46.489030+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":389,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-50-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-50-push_T-standard-s0-scene1.json"},{"created_at":"2026-11-01T05:49:00.180998+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":587,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:18:37.110947+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":640,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-52-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-52-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:19:29.436449+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-53-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-53-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:32:47.618839+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":171,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-54-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-54-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:42:06.528677+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-55-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-55-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:46:36.526230+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":183,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-56-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-56-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:01:29.981997+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":751,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-11-01T06:41:54.147153+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":491,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-58-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-58-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-11-01T06:28:55.617135+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":59,"model_responses":59,"native_controls":541,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-59-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-59-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:27:32.421669+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":400,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:36:08.288496+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-61-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-61-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:27:26.043770+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":373,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-62-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-62-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:01:08.133735+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":395,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-63-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-63-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-11-01T07:39:26.761890+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":800,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-64-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-64-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-11-01T07:05:33.377064+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":664,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-65-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-65-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:11:38.936172+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":364,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-66-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-66-swap_T-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:02:40.902736+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":342,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-67-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-67-swap_T-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:29:14.564242+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r1-keyframes-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r1-keyframes-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r1","score_scale":"0..1"},"run_id":"r1-dev69-20261030-68-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r1-dev69-20261030-68-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-30T14:44:36.936450+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":165,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-00-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-00-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:44:01.048835+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-01-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-01-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:51:24.511098+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":193,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-02-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-02-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:08:09.900389+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":599,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-03-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-03-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-11-01T11:18:07.446776+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":904,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-04-enospc-rerun1-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-04-enospc-rerun1-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-11-01T07:07:25.702490+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":627,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-05-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-05-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:01:53.684706+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":964,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-06-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-06-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:01:53.701548+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":1093,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-07-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-07-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-11-01T07:12:17.279293+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1074,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-08-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-08-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:58:33.346294+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":1041,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:52:49.648940+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":1003,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-10-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-10-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-01T08:10:11.844251+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-11-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-11-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:34:59.602169+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":468,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-12-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-12-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-01T06:29:48.185549+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":489,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-13-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-13-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:19:15.379294+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":458,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-14-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-14-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:12:17.170158+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1322,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-15-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-15-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:01:07.712200+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1620,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-16-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-16-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-11-01T07:35:06.900686+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1184,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-17-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-17-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:06:32.002781+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":397,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-18-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-18-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-11-01T10:35:16.998330+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":413,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-19-enospc-rerun1-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-19-enospc-rerun1-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-11-01T09:17:48.302406+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-20-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-20-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:14:49.739028+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":19,"model_responses":19,"native_controls":101,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-21-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-21-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:10:51.713371+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":136,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-22-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-22-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-11-01T07:13:31.926056+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":197,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-23-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-23-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-11-01T08:03:46.444788+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1372,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-11-01T11:32:57.291896+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1463,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-25-enospc-rerun1-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-25-enospc-rerun1-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-11-01T08:23:45.863182+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":1324,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-26-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-26-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-11-01T08:27:53.612616+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":497,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:54:06.573280+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":512,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-28-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-28-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-11-01T06:51:50.814133+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":564,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-29-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-29-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-11-01T06:52:52.769110+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":1022,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-11-01T11:17:31.629610+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1064,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-31-enospc-rerun1-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-31-enospc-rerun1-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-11-01T07:55:49.533495+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":97,"model_responses":97,"native_controls":1169,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-32-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-32-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:48:53.782596+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":435,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-11-01T10:41:32.262212+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":513,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-34-enospc-rerun1-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-34-enospc-rerun1-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-11-01T09:17:47.785210+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":527,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-35-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-35-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-11-01T09:19:55.188179+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":69,"model_responses":69,"native_controls":394,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-36-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-36-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:49:30.795631+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":450,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-37-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-37-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-11-01T07:49:48.715112+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-38-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-38-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:38:12.956113+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-39-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-39-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-11-01T08:19:09.895776+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":370,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-40-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-40-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-11-01T09:18:15.626129+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":352,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-41-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-41-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-11-01T08:37:35.092105+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":387,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-11-01T08:46:33.512354+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":600,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-43-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-43-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-11-01T08:09:14.323036+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":520,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-44-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-44-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:05:56.809772+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":316,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-45-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-45-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:04:48.218100+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":303,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-46-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-46-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-11-01T09:11:45.157447+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":302,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-47-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-47-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-11-01T08:19:51.376899+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":297,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-48-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-48-push_T-standard-s0-scene0.json"},{"created_at":"2026-11-01T08:17:27.309805+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":336,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-49-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-49-push_T-random-s0-scene1.json"},{"created_at":"2026-11-01T09:32:37.258517+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":429,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-50-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-50-push_T-standard-s0-scene1.json"},{"created_at":"2026-11-01T09:21:08.270146+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":651,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-11-01T09:18:24.818980+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":663,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-52-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-52-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-11-01T08:08:26.627245+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":693,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-53-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-53-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-11-01T07:59:36.301166+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":208,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-54-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-54-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-11-01T08:05:13.987721+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":274,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-55-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-55-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-11-01T08:28:10.211304+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":172,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-56-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-56-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-11-01T09:30:00.164783+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":910,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-11-01T09:07:42.519106+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":709,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-58-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-58-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-11-01T09:05:54.087477+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":493,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-59-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-59-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-11-01T08:21:27.993226+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":395,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-01T07:20:56.358890+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":373,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-61-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-61-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-01T07:18:12.909075+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-62-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-62-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-01T09:34:51.120355+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":406,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-63-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-63-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-11-01T08:34:10.680614+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":409,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-64-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-64-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-11-01T08:45:25.242166+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":735,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-65-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-65-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-11-01T09:28:53.675412+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":385,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-66-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-66-swap_T-standard-s0-scene1.json"},{"created_at":"2026-11-01T09:30:56.900826+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":280,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-67-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-67-swap_T-standard-s0-scene2.json"},{"created_at":"2026-11-01T09:32:40.325159+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"l3-r2-precision8-20261019-v1","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"l3-r2-precision8-20261019-v1","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-r2","score_scale":"0..1"},"run_id":"r2-dev69-20261030-68-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/r2-dev69-20261030-68-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-23T10:42:07.345549+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":462,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c000-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c000-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-23T10:38:44.397998+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":353,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c001-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c001-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:33:01.752159+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":143,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c002-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c002-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:52:17.339397+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":924,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c003-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c003-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:51:25.931634+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":888,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c004-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c004-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-23T10:37:46.938078+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":285,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c005-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c005-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:41:03.479267+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":511,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c006-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c006-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:55:33.489780+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1032,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c007-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c007-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:52:14.776575+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":396,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c008-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c008-push_T-random-s0-scene0.json"},{"created_at":"2026-10-23T10:51:43.891415+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":648,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c009-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c009-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-23T10:46:15.748457+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":490,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c010-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c010-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:34:23.529147+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":176,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c011-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c011-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:42:59.889098+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":686,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c012-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c012-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:43:05.405029+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":452,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c013-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c013-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-23T10:34:13.228928+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":269,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c014-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c014-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:45:58.448716+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":575,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c015-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c015-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:02:02.278401+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":1050,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c016-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c016-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:51:43.799059+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":629,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c017-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c017-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-23T10:54:40.342980+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":821,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c018-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c018-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-23T11:04:58.822940+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":878,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c019-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c019-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:02:19.369396+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":680,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c020-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c020-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:04:19.499343+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":806,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c021-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c021-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:57:37.052070+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":437,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c022-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c022-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-23T11:04:15.158122+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":494,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c023-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c023-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:16:20.170350+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":751,"native_terminal":true,"score":0.6,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c024-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c024-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-23T10:57:35.988538+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":418,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c025-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c025-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:11:43.788709+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":639,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c026-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c026-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-23T11:02:47.124147+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":302,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c027-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c027-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:10:08.388152+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":451,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c028-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c028-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:04:46.528085+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c029-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c029-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:09:35.304237+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":631,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c030-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c030-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-23T11:04:38.160122+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":302,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c031-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c031-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:21:02.852484+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":1082,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c032-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c032-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:34:01.705476+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":881,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c033-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c033-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:23:37.853879+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":783,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c034-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c034-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-23T11:09:36.399623+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":333,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c035-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c035-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:15:50.116119+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":354,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c036-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c036-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-23T11:54:04.557821+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":103,"native_controls":1019,"native_terminal":true,"score":0.75,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c037-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c037-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:28:26.522780+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":58,"model_responses":58,"native_controls":1363,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c038-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c038-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:15:13.921133+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c039-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c039-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:24:11.642156+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":615,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c040-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c040-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-23T11:24:28.466101+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":704,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-semantic-eef","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-final42-995480fe-20261023-c041-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-final42-995480fe-20261023-c041-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-11-01T11:45:27.025183+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":181,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-01T11:44:19.214409+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":193,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-01T11:44:28.015208+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":175,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-01T11:59:57.963099+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":575,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-11-01T11:56:20.928115+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":572,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-11-01T11:53:42.472666+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":425,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-11-01T12:33:00.371070+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":809,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-11-01T12:44:15.185937+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":1069,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-11-01T12:53:24.450314+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":1018,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-11-01T13:03:17.750846+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":1041,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-01T13:09:35.918741+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":1020,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-01T13:16:56.710682+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":917,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-01T12:53:39.440014+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":440,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-11-01T12:41:44.429986+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":506,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-11-01T12:39:57.838306+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":511,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-11-01T12:46:40.262717+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":349,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-11-01T12:49:00.306276+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":668,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-11-01T13:50:58.712502+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":984,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-11-01T13:53:36.337645+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":500,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-11-01T13:24:17.766159+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":316,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-11-01T13:46:50.493121+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":316,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-11-01T13:55:44.577392+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":11,"model_responses":11,"native_controls":96,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-11-01T14:05:44.396027+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":22,"model_responses":22,"native_controls":130,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-11-01T14:12:25.896851+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":196,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-11-01T15:47:18.884439+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":74,"native_controls":1584,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-11-01T15:36:43.976167+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":56,"native_controls":1600,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-11-01T15:51:25.421602+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":1319,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-11-01T15:28:39.394771+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":509,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-11-01T15:53:13.839605+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":480,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-11-01T15:13:16.363362+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":296,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-11-01T15:59:08.901897+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":665,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-11-01T17:05:19.162929+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":991,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-11-01T17:14:59.384843+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":1019,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-11-01T15:38:57.826907+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":239,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-11-01T16:45:33.588865+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":523,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-11-01T16:20:30.449072+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":526,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-11-01T16:36:28.980983+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":489,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-11-01T16:35:06.105392+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-11-01T16:00:12.669346+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":495,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-11-01T16:00:30.829067+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":369,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-11-01T15:48:06.260364+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":342,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-11-01T16:19:21.179177+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":312,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-11-01T16:51:09.108423+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":585,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-11-01T16:40:52.223339+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":386,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-11-01T16:20:31.890780+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":15,"model_responses":15,"native_controls":130,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-11-01T16:44:49.247587+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":343,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-11-01T16:43:55.427594+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":302,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-11-01T16:46:11.943378+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":314,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-11-01T18:22:37.322828+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":455,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-push_T-random-s0-scene1.json"},{"created_at":"2026-11-01T18:07:51.392967+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene0.json"},{"created_at":"2026-11-01T18:12:32.644813+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":378,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene1.json"},{"created_at":"2026-11-01T17:50:28.029336+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":695,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-11-01T17:20:49.354584+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":569,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-11-01T17:45:58.122961+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":700,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-11-01T17:09:19.260479+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":186,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-11-01T17:11:16.061380+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-11-01T17:16:24.196951+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":23,"model_responses":23,"native_controls":213,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-11-01T18:41:14.329368+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":1033,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-11-01T18:02:00.172332+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":703,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-11-01T17:43:54.045825+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":277,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-11-01T17:59:05.185763+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-11-01T17:53:50.520949+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":371,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-11-01T17:51:55.955654+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":325,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-11-01T18:29:07.849249+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":721,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-11-01T18:03:36.664893+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":316,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-11-01T18:34:10.903337+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":792,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-11-01T18:08:21.685133+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene1.json"},{"created_at":"2026-11-01T18:13:14.893665+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene2.json"},{"created_at":"2026-11-01T18:15:52.014904+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"rsi-semantic-eef","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"rsi-final42-995480fe-20261023","max_decisions":100,"native_control_cap":20,"profile":"rsi_semantic_eef","score_scale":"0..1"},"run_id":"rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-19T15:20:56.527325+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":185,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-align-blocks-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-align-blocks-cap20-20261019-2151-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-align-blocks-cap20-20261019-2151-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:37:22.429614+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":754,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-arrange-largest-number-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-arrange-largest-number-cap20-20261019-2151-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-arrange-largest-number-cap20-20261019-2151-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-19T15:40:23.172021+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":825,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"semantic-eef-build-tower-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-build-tower-cap20-20261019-2151-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-build-tower-cap20-20261019-2151-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-19T13:11:18.996692+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":1075,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"semantic-eef-classify-cap20-20261019-2039","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-classify-cap20-20261019-2039-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-classify-cap20-20261019-2039-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-19T16:09:07.707368+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":1018,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-classify-objects-by-language-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-classify-objects-by-language-cap20-20261019-2151-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-classify-objects-by-language-cap20-20261019-2151-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-19T12:16:47.858789+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":287,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"semantic-eef-coin-cap20-20261019-1955","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-coin-cap20-20261019-1955-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-coin-cap20-20261019-1955-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-19T16:06:45.569030+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":542,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-cover-blocks-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-cover-blocks-cap20-20261019-2151-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-cover-blocks-cap20-20261019-2151-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-20T15:03:10.852110+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:08:34.960173+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:16:49.761034+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":182,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-20T17:50:03.386815+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":834,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-random-s0-scene1.json"},{"created_at":"2026-10-20T17:34:10.903548+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":933,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene0.json"},{"created_at":"2026-10-20T18:49:18.622183+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":578,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene1.json"},{"created_at":"2026-10-20T17:21:36.154425+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":800,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene1.json"},{"created_at":"2026-10-20T17:44:59.234320+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":873,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene2.json"},{"created_at":"2026-10-20T19:28:54.199802+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":873,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:44:31.798114+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":1070,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-20T17:38:37.461969+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-20T17:12:42.726795+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":812,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:13:51.879220+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":730,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:52:56.152103+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":774,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:54:49.697282+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":543,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:34:03.378856+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":795,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene1.json"},{"created_at":"2026-10-20T17:54:43.924682+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":679,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:28:09.310662+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":817,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene3.json"},{"created_at":"2026-10-20T16:23:16.906330+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":369,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-random-s0-scene1.json"},{"created_at":"2026-10-20T15:59:30.106236+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":50,"model_responses":50,"native_controls":425,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene0.json"},{"created_at":"2026-10-20T16:39:20.157800+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":327,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene1.json"},{"created_at":"2026-10-20T14:35:01.092807+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":8,"model_responses":8,"native_controls":66,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene1.json"},{"created_at":"2026-10-20T17:26:56.551649+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":193,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:05:36.101268+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":180,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene3.json"},{"created_at":"2026-10-20T17:39:31.874910+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":101,"native_controls":1352,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene1.json"},{"created_at":"2026-10-20T18:03:56.031992+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":1531,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:44:52.930349+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":1349,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene3.json"},{"created_at":"2026-10-20T15:02:56.888825+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":410,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:42:29.173478+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":67,"model_responses":67,"native_controls":455,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene2.json"},{"created_at":"2026-10-20T16:24:40.035050+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":383,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene3.json"},{"created_at":"2026-10-20T18:11:10.630800+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1089,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-random-s0-scene1.json"},{"created_at":"2026-10-20T17:03:20.175110+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":830,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene0.json"},{"created_at":"2026-10-20T18:51:59.809263+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":875,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene1.json"},{"created_at":"2026-10-20T14:50:39.079250+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":196,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene1.json"},{"created_at":"2026-10-20T18:28:40.620506+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":549,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:42:27.165913+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":230,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene3.json"},{"created_at":"2026-10-20T17:09:11.376592+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene1.json"},{"created_at":"2026-10-20T17:49:45.674796+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene2.json"},{"created_at":"2026-10-20T17:31:13.545862+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene3.json"},{"created_at":"2026-10-20T15:17:49.110513+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":305,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:56:08.108623+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:12:44.381793+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":339,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene3.json"},{"created_at":"2026-10-20T18:03:22.668196+00:00","episode":{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":476,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene1.json"},{"created_at":"2026-10-20T18:30:12.910580+00:00","episode":{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":57,"model_responses":57,"native_controls":584,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:59:27.962898+00:00","episode":{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":297,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene3.json"},{"created_at":"2026-10-20T15:21:49.056831+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":399,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:21:49.838418+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":361,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene2.json"},{"created_at":"2026-10-20T17:45:10.094543+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":354,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene3.json"},{"created_at":"2026-10-20T18:05:27.231348+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":367,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-push_T-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-push_T-random-s0-scene1.json"},{"created_at":"2026-10-20T14:50:17.126117+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":142,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene0.json"},{"created_at":"2026-10-20T17:42:58.557486+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":339,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:47:50.245432+00:00","episode":{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":696,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:39:18.194827+00:00","episode":{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":662,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:13:55.033255+00:00","episode":{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":688,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene3.json"},{"created_at":"2026-10-20T15:02:30.264156+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":232,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:00:14.893844+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":272,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:59:16.688622+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":258,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene3.json"},{"created_at":"2026-10-20T18:45:55.525609+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":974,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-random-s0-scene1.json"},{"created_at":"2026-10-20T15:21:45.563638+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":430,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene0.json"},{"created_at":"2026-10-20T18:22:47.572110+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":72,"model_responses":72,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:06:16.931602+00:00","episode":{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":389,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene1.json"},{"created_at":"2026-10-20T16:01:47.466987+00:00","episode":{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":400,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene2.json"},{"created_at":"2026-10-20T18:20:02.536722+00:00","episode":{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":311,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene3.json"},{"created_at":"2026-10-20T18:04:10.069499+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":797,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-random-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-random-s0-scene1.json"},{"created_at":"2026-10-20T14:59:34.290297+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":301,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene0.json"},{"created_at":"2026-10-20T18:40:32.151020+00:00","episode":{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":635,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:01:23.807877+00:00","episode":{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene1","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene1.json"},{"created_at":"2026-10-20T15:36:06.580455+00:00","episode":{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":338,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene2.json"},{"created_at":"2026-10-20T16:20:27.586542+00:00","episode":{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene3","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene3.json"},{"created_at":"2026-10-19T15:36:44.927821+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":782,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-fasten-screws-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-fasten-screws-cap20-20261019-2151-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-fasten-screws-cap20-20261019-2151-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:53:41.971694+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":641,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"semantic-eef-fill-egg-holder-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-fill-egg-holder-cap20-20261019-2151-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-fill-egg-holder-cap20-20261019-2151-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:37:10.321831+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":887,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-fill-pen-holder-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-fill-pen-holder-cap20-20261019-2151-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-fill-pen-holder-cap20-20261019-2151-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:02:53.106467+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":332,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-fold-clothes-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-fold-clothes-cap20-20261019-2151-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-fold-clothes-cap20-20261019-2151-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-19T15:26:04.883668+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":17,"model_responses":17,"native_controls":111,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-general-pickup-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-general-pickup-cap20-20261019-2151-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-general-pickup-cap20-20261019-2151-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-19T13:10:25.790750+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":633,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-hang-mugs-cap20-20261019-2039","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-hang-mugs-cap20-20261019-2039-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-hang-mugs-cap20-20261019-2039-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-19T16:28:47.361820+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":93,"native_controls":1415,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-imitate-sorting-sequence-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-imitate-sorting-sequence-cap20-20261019-2151-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-imitate-sorting-sequence-cap20-20261019-2151-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-19T14:56:40.285119+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":271,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"semantic-eef-insert-key-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-insert-key-cap20-20261019-2151-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-insert-key-cap20-20261019-2151-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-19T12:58:29.532473+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-insert-tubes-cap20-20261019-2039","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-insert-tubes-cap20-20261019-2039-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-insert-tubes-cap20-20261019-2039-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:48:46.844909+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":85,"model_responses":85,"native_controls":515,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-kong-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-make-kong-cap20-20261019-2151-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-make-kong-cap20-20261019-2151-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:43:42.997760+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":767,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-make-toast-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-make-toast-cap20-20261019-2151-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-make-toast-cap20-20261019-2151-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-19T16:00:24.543601+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":320,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-19T16:31:10.522329+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":795,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-organize-table-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-organize-table-cap20-20261019-2151-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-organize-table-cap20-20261019-2151-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-19T12:27:59.946645+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":86,"model_responses":86,"native_controls":916,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-pack-cap20-20261019-1955","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-pack-cap20-20261019-1955-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-pack-cap20-20261019-1955-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-19T16:04:12.822919+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":511,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-19T16:02:31.527367+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":540,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"semantic-eef-play-stacking-toy-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-play-stacking-toy-cap20-20261019-2151-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-play-stacking-toy-cap20-20261019-2151-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:25:57.015831+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":250,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"semantic-eef-play-tic-tac-toe-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-play-tic-tac-toe-cap20-20261019-2151-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-play-tic-tac-toe-cap20-20261019-2151-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:12:32.892864+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":280,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-play-xylophone-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-play-xylophone-cap20-20261019-2151-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-play-xylophone-cap20-20261019-2151-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-19T13:36:23.658846+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":330,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-plug-charger-cap20-20261019-2123","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-plug-charger-cap20-20261019-2123-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-plug-charger-cap20-20261019-2123-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-19T16:37:47.816529+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":743,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-pour-by-language-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-pour-by-language-cap20-20261019-2151-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-pour-by-language-cap20-20261019-2151-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-19T12:22:21.613715+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":60,"model_responses":60,"native_controls":588,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-pour-cap20-20261019-1955","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-pour-cap20-20261019-1955-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-pour-cap20-20261019-1955-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:03:06.151057+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":44,"model_responses":44,"native_controls":370,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-pour-liquid-into-cup-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-pour-liquid-into-cup-cap20-20261019-2151-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-pour-liquid-into-cup-cap20-20261019-2151-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-19T15:36:37.773624+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":345,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-press-by-number-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-press-by-number-cap20-20261019-2151-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-press-by-number-cap20-20261019-2151-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:18:25.195971+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":260,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-push-t-cap20-retry1-20261019-2247","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-push-t-cap20-retry1-20261019-2247-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-push-t-cap20-retry1-20261019-2247-push_T-random-s0-scene0.json"},{"created_at":"2026-10-19T15:18:32.929489+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":660,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:58:33.646219+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":289,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-solve-equation-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-solve-equation-cap20-20261019-2151-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-solve-equation-cap20-20261019-2151-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:27:03.788439+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":646,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-19T15:46:07.697411+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":385,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-stack-blocks-by-language-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-stack-blocks-by-language-cap20-20261019-2151-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-stack-blocks-by-language-cap20-20261019-2151-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:16:50.843198+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":61,"model_responses":61,"native_controls":550,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"semantic-eef-stack-blocks-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-stack-blocks-cap20-20261019-2151-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-stack-blocks-cap20-20261019-2151-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-19T13:45:34.788341+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":530,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"semantic-eef-stack-bowls-cap20-20261019-2123","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-stack-bowls-cap20-20261019-2123-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-stack-bowls-cap20-20261019-2123-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-19T15:41:26.175350+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":763,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-store-laptop-and-headphones-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-store-laptop-and-headphones-cap20-20261019-2151-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-store-laptop-and-headphones-cap20-20261019-2151-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-19T16:41:20.276448+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":850,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-store-tools-in-toolbox-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-store-tools-in-toolbox-cap20-20261019-2151-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-store-tools-in-toolbox-cap20-20261019-2151-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:52:21.028973+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":447,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-swap-blocks-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-swap-blocks-cap20-20261019-2151-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-swap-blocks-cap20-20261019-2151-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-19T16:00:27.662832+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":363,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-swap-t-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-swap-t-cap20-20261019-2151-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-swap-t-cap20-20261019-2151-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-19T15:26:07.197552+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"semantic-eef-cap20-20261019","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":680,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"semantic-eef-sweep-blocks-cap20-20261019-2151","max_decisions":100,"native_control_cap":20,"profile":"custom-semantic-eef","score_scale":"0..1"},"run_id":"semantic-eef-sweep-blocks-cap20-20261019-2151-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/semantic-eef-sweep-blocks-cap20-20261019-2151-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-12T15:39:26.973383+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":456,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-smoke-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-20261012-stackblocks-repair01-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-20261012-stackblocks-repair01-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-13T04:12:55.343832+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":32,"model_responses":32,"native_controls":173,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:29:04.672735+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:07:46.831762+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":12,"model_responses":12,"native_controls":76,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-general_pickup-standard-s0-scene0.json"},{"created_at":null,"episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"user_accepted_supplementary","formal_episode_result":false,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":true}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"native_controls":1404,"score":1.0,"status":"accepted_simplified","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:38:40.910252+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":46,"model_responses":46,"native_controls":512,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:49:06.964424+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":813,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:32:59.268382+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":254,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:17:55.421129+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":382,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:47:45.160863+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":34,"model_responses":34,"native_controls":282,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:17:34.262762+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":294,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:55:57.282909+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":851,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-13T04:17:33.503014+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local13-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local13-20261013-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local13-20261013-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:40:59.719170+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":938,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-12T17:00:25.125343+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1010,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:59:05.575912+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":258,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:29:30.046659+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":1024,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-12T17:03:32.955352+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":970,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-12T15:38:24.120734+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":286,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-12T15:57:49.662534+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":719,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-12T16:46:02.249365+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":20,"model_responses":20,"native_controls":244,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:15:06.507272+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":427,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:26:00.280747+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":727,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-12T16:05:03.562169+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":1048,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-12T16:55:44.824500+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":74,"model_responses":74,"native_controls":479,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:21:00.290619+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":49,"model_responses":49,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-12T15:39:29.716046+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-12T15:51:30.895755+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":447,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-push_T-random-s0-scene0.json"},{"created_at":"2026-10-12T16:57:50.863918+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":691,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-12T16:34:56.466020+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":908,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-12T15:47:22.672606+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":503,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-12T16:38:08.185566+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":619,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-store_laptop_and_headphones-random-s0-scene0.json"},{"created_at":"2026-10-12T15:55:07.309979+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":83,"model_responses":83,"native_controls":584,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-local42-20261012","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-local42-20261012-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-local42-20261012-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-13T06:02:36.095982+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":910,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:44:34.359004+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":499,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-13T06:21:22.757415+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":415,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:56:53.706786+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":587,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:36:34.990310+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":340,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-13T06:04:32.154123+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":921,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:38:26.196908+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":344,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:37:32.135648+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":41,"model_responses":41,"native_controls":321,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-13T05:49:23.168210+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-cap20-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":56,"model_responses":56,"native_controls":443,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-persistent-cap20-medium-retry9-20261013","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-medium-retry9-20261013-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-medium-retry9-20261013-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-14T13:55:33.159222+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":344,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-fold_clothes-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-fold_clothes-random-s0-scene4.json"},{"created_at":"2026-10-14T14:24:08.833889+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"model_responses":76,"native_controls":565,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-hang_mugs-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-hang_mugs-random-s0-scene4.json"},{"created_at":"2026-10-14T14:11:02.806018+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":384,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-make_toast-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-make_toast-random-s0-scene4.json"},{"created_at":"2026-10-14T14:39:27.336343+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":822,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-pack_objects_into_box-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-pack_objects_into_box-random-s0-scene4.json"},{"created_at":"2026-10-14T14:29:02.919348+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":324,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-plug_in_charger-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-plug_in_charger-standard-s0-scene4.json"},{"created_at":"2026-10-14T14:05:07.138343+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-pour_liquid_into_cup-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-pour_liquid_into_cup-random-s0-scene4.json"},{"created_at":"2026-10-14T14:25:45.119944+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":560,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-push_T-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-push_T-random-s0-scene4.json"},{"created_at":"2026-10-14T14:24:46.747107+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":336,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-stack_blocks-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-stack_blocks-random-s0-scene4.json"},{"created_at":"2026-10-14T14:22:18.978057+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":786,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-stack_bowls-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-stack_bowls-random-s0-scene4.json"},{"created_at":"2026-10-14T14:07:24.527345+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":501,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-20261014-sweep_blocks-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-20261014-sweep_blocks-random-s0-scene4.json"},{"created_at":"2026-10-14T15:57:34.936246+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":73,"model_responses":73,"native_controls":760,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart01-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart01-20261014-fill_pen_holder-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart01-20261014-fill_pen_holder-standard-s0-scene4.json"},{"created_at":"2026-10-14T15:42:35.799814+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":53,"model_responses":53,"native_controls":497,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart01-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart01-20261014-insert_tubes-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart01-20261014-insert_tubes-standard-s0-scene4.json"},{"created_at":"2026-10-14T15:37:54.011391+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":414,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene4-medium-restart01-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart01-20261014-pour_balls_into_vase-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart01-20261014-pour_balls_into_vase-standard-s0-scene4.json"},{"created_at":"2026-10-14T15:56:35.864032+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":651,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart01-20261014","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart01-20261014-store_laptop_and_headphones-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart01-20261014-store_laptop_and_headphones-random-s0-scene4.json"},{"created_at":"2026-10-15T03:44:59.701885+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-align_blocks-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-align_blocks-standard-s0-scene4.json"},{"created_at":"2026-10-15T02:03:12.360727+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":440,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-arrange_largest_number-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-arrange_largest_number-random-s0-scene4.json"},{"created_at":"2026-10-15T02:40:45.331713+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":802,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-build_tower-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-build_tower-standard-s0-scene4.json"},{"created_at":"2026-10-15T02:53:22.490107+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":1022,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-classify_objects-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-classify_objects-standard-s0-scene4.json"},{"created_at":"2026-10-15T02:34:26.985669+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":273,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-deposit_coin-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-deposit_coin-standard-s0-scene4.json"},{"created_at":"2026-10-15T03:08:19.705660+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":936,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-fasten_screws-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-fasten_screws-standard-s0-scene4.json"},{"created_at":"2026-10-15T01:55:30.150858+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":284,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-insert_key-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-insert_key-standard-s0-scene4.json"},{"created_at":"2026-10-15T03:20:02.572062+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":543,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-make_kong-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-make_kong-standard-s0-scene4.json"},{"created_at":"2026-10-15T02:04:16.079127+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":51,"model_responses":51,"native_controls":429,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-match_and_pick_from_conveyor-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-match_and_pick_from_conveyor-standard-s0-scene4.json"},{"created_at":"2026-10-15T03:41:34.728815+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":275,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-pick_from_conveyor_by_image-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-pick_from_conveyor_by_image-standard-s0-scene4.json"},{"created_at":"2026-10-15T03:11:37.871245+00:00","episode":{"capability":"Precision","scene":4,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":466,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-play_Xylophone-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-play_Xylophone-standard-s0-scene4.json"},{"created_at":"2026-10-15T03:54:05.987652+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":99,"model_responses":99,"native_controls":568,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-play_stacking_toy-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-play_stacking_toy-standard-s0-scene4.json"},{"created_at":"2026-10-15T02:26:00.828319+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":280,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-play_tic_tac_toe-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-play_tic_tac_toe-standard-s0-scene4.json"},{"created_at":"2026-10-15T03:55:18.856708+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":62,"model_responses":62,"native_controls":636,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-put_bottles_into_dustbin-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-put_bottles_into_dustbin-standard-s0-scene4.json"},{"created_at":"2026-10-15T02:22:30.598117+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":192,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-solve_equation-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-solve_equation-standard-s0-scene4.json"},{"created_at":"2026-10-15T02:03:30.057273+00:00","episode":{"capability":"Generalization","scene":4,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","preserved_unselected":false,"rounds":[9],"selected":true,"selection_id":"persistent-cap20-random-scene4","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":410,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-sort_nesting_dolls_by_size-random-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-sort_nesting_dolls_by_size-random-s0-scene4.json"},{"created_at":"2026-10-15T03:15:55.869657+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":39,"model_responses":39,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-swap_T-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-swap_T-standard-s0-scene4.json"},{"created_at":"2026-10-15T03:39:08.049092+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":52,"model_responses":52,"native_controls":379,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart02-20261015-swap_blocks-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart02-20261015-swap_blocks-standard-s0-scene4.json"},{"created_at":"2026-10-15T05:02:15.120192+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":120,"native_controls":698,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart03-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart03-20261015-classify_objects_by_language-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart03-20261015-classify_objects_by_language-standard-s0-scene4.json"},{"created_at":"2026-10-15T04:27:06.280497+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":4,"model_responses":5,"native_controls":62,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart03-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart03-20261015-cover_blocks-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart03-20261015-cover_blocks-standard-s0-scene4.json"},{"created_at":"2026-10-15T04:31:34.979436+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":26,"native_controls":200,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart03-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart03-20261015-general_pickup-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart03-20261015-general_pickup-standard-s0-scene4.json"},{"created_at":"2026-10-15T05:09:17.031974+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":81,"native_controls":741,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart03-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart03-20261015-organize_table-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart03-20261015-organize_table-standard-s0-scene4.json"},{"created_at":"2026-10-15T04:43:23.767291+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":38,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart03-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart03-20261015-stack_blocks_by_language-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart03-20261015-stack_blocks_by_language-standard-s0-scene4.json"},{"created_at":"2026-10-15T10:19:18.509151+00:00","episode":{"capability":"Long-Horizon","scene":4,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":79,"model_responses":79,"native_controls":655,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart07-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart07-20261015-fill_egg_holder-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart07-20261015-fill_egg_holder-standard-s0-scene4.json"},{"created_at":"2026-10-15T10:11:21.888200+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":55,"model_responses":55,"native_controls":771,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart07-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart07-20261015-pour_by_language-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart07-20261015-pour_by_language-standard-s0-scene4.json"},{"created_at":"2026-10-15T09:55:39.777002+00:00","episode":{"capability":"Memory","scene":4,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":267,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene4-medium-restart07-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart07-20261015-press_by_number-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart07-20261015-press_by_number-standard-s0-scene4.json"},{"created_at":"2026-10-15T10:23:41.441569+00:00","episode":{"capability":"Open","scene":4,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[5],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":92,"model_responses":92,"native_controls":870,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene4-medium-restart07-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene4-medium-restart07-20261015-store_tools_in_toolbox-standard-s0-scene4","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene4-medium-restart07-20261015-store_tools_in_toolbox-standard-s0-scene4.json"},{"created_at":"2026-10-15T12:24:17.944323+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"fold_clothes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":306,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-20261015-fold_clothes-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-20261015-fold_clothes-standard-s0-scene2.json"},{"created_at":"2026-10-15T12:41:36.590191+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"hang_mugs","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":602,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-20261015-hang_mugs-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-20261015-hang_mugs-standard-s0-scene2.json"},{"created_at":"2026-10-15T12:48:06.310794+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"make_toast","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":712,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-20261015-make_toast-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-20261015-make_toast-standard-s0-scene2.json"},{"created_at":"2026-10-15T12:48:01.898651+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"pack_objects_into_box","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":849,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-20261015-pack_objects_into_box-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-20261015-pack_objects_into_box-standard-s0-scene2.json"},{"created_at":"2026-10-15T12:21:44.576483+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":28,"model_responses":28,"native_controls":284,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-20261015-pour_liquid_into_cup-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-20261015-pour_liquid_into_cup-standard-s0-scene2.json"},{"created_at":"2026-10-15T12:26:47.411985+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"stack_bowls","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":511,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-20261015-stack_bowls-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-20261015-stack_bowls-standard-s0-scene2.json"},{"created_at":"2026-10-15T12:45:34.078672+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"sweep_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":84,"model_responses":84,"native_controls":606,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-20261015-sweep_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-20261015-sweep_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-16T02:15:40.348123+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":68,"model_responses":68,"native_controls":791,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-final01-20261016","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-final01-20261016-pour_by_language-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-final01-20261016-pour_by_language-standard-s0-scene5.json"},{"created_at":"2026-10-15T13:05:58.640577+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"arrange_largest_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":648,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-arrange_largest_number-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-arrange_largest_number-standard-s0-scene2.json"},{"created_at":"2026-10-15T13:48:15.075389+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":904,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-build_tower-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-build_tower-standard-s0-scene5.json"},{"created_at":"2026-10-15T13:17:00.027397+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":646,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-classify_objects-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-classify_objects-standard-s0-scene5.json"},{"created_at":"2026-10-15T13:46:22.856363+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":921,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-fasten_screws-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-fasten_screws-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:31:09.807144+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":75,"model_responses":75,"native_controls":665,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-fill_pen_holder-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-fill_pen_holder-standard-s0-scene5.json"},{"created_at":"2026-10-15T13:52:18.491737+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":235,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-insert_key-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-insert_key-standard-s0-scene5.json"},{"created_at":"2026-10-15T12:47:47.046576+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-insert_tubes-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-insert_tubes-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:58:58.042934+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":91,"model_responses":91,"native_controls":452,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-make_kong-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-make_kong-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:40:49.442213+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":500,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-play_Xylophone-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-play_Xylophone-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:59:59.425816+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":95,"model_responses":95,"native_controls":656,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-play_stacking_toy-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-play_stacking_toy-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:39:24.135184+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":267,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-play_tic_tac_toe-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-play_tic_tac_toe-standard-s0-scene5.json"},{"created_at":"2026-10-15T13:11:57.684355+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":40,"model_responses":40,"native_controls":340,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-plug_in_charger-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-plug_in_charger-standard-s0-scene5.json"},{"created_at":"2026-10-15T13:06:49.928580+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":245,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-pour_balls_into_vase-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-pour_balls_into_vase-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:28:05.846688+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"push_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":71,"model_responses":71,"native_controls":508,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-push_T-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-push_T-standard-s0-scene2.json"},{"created_at":"2026-10-15T14:48:42.766656+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":695,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-put_bottles_into_dustbin-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-put_bottles_into_dustbin-standard-s0-scene5.json"},{"created_at":"2026-10-15T12:40:13.714623+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"stack_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":237,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-stack_blocks-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-stack_blocks-standard-s0-scene2.json"},{"created_at":"2026-10-15T13:31:12.245246+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":552,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-store_laptop_and_headphones-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-store_laptop_and_headphones-standard-s0-scene2.json"},{"created_at":"2026-10-15T14:02:33.977897+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":54,"model_responses":54,"native_controls":390,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-swap_blocks-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued01-20261015-swap_blocks-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:15:39.997534+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":42,"model_responses":42,"native_controls":176,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-align_blocks-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-align_blocks-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:59:59.286458+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":780,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-classify_objects_by_language-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-classify_objects_by_language-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:27:18.004561+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":800,"native_terminal":true,"score":0.05,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-cover_blocks-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-cover_blocks-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:12:12.034846+00:00","episode":{"capability":"Precision","scene":5,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":27,"model_responses":27,"native_controls":268,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-deposit_coin-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-deposit_coin-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:19:26.158580+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-fill_egg_holder-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-fill_egg_holder-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:09:23.786983+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":13,"model_responses":13,"native_controls":128,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-general_pickup-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-general_pickup-standard-s0-scene5.json"},{"created_at":"2026-10-15T16:24:46.842460+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":1500,"native_terminal":true,"score":0.05,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-imitate_sorting_sequence-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-imitate_sorting_sequence-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:11:35.917081+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":550,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-match_and_pick_from_conveyor-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-match_and_pick_from_conveyor-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:42:43.584727+00:00","episode":{"capability":"Long-Horizon","scene":5,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":88,"model_responses":88,"native_controls":804,"native_terminal":true,"score":0.25,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-organize_table-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-organize_table-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:09:53.830626+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":26,"model_responses":26,"native_controls":250,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-pick_from_conveyor_by_image-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-pick_from_conveyor_by_image-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:32:05.770242+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":31,"model_responses":31,"native_controls":280,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-press_by_number-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-press_by_number-standard-s0-scene5.json"},{"created_at":"2026-10-15T15:23:50.930314+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":29,"model_responses":29,"native_controls":239,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-solve_equation-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-solve_equation-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:57:06.378277+00:00","episode":{"capability":"Generalization","scene":2,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":65,"model_responses":65,"native_controls":634,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-sort_nesting_dolls_by_size-standard-s0-scene2","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-sort_nesting_dolls_by_size-standard-s0-scene2.json"},{"created_at":"2026-10-15T15:41:19.799255+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":313,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-stack_blocks_by_language-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-stack_blocks_by_language-standard-s0-scene5.json"},{"created_at":"2026-10-15T16:05:38.552752+00:00","episode":{"capability":"Open","scene":5,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":90,"model_responses":90,"native_controls":757,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-store_tools_in_toolbox-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-store_tools_in_toolbox-standard-s0-scene5.json"},{"created_at":"2026-10-15T14:55:43.586748+00:00","episode":{"capability":"Memory","scene":5,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","preserved_unselected":false,"rounds":[6],"selected":true,"selection_id":"medium-cap20-rounds4-v2","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":318,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"},"run_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-swap_T-standard-s0-scene5","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-cap20-scene5-genstandard2-medium-queued02-20261015-swap_T-standard-s0-scene5.json"},{"created_at":null,"episode":{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},"evidence_level":"user_accepted_supplementary","formal_episode_result":false,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":true}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":76,"native_controls":1430,"score":1.0,"status":"accepted_simplified","success":true},"protocol":{"id":"thunlp-full-ik-imitate-retry01-20261014","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0.json"},{"created_at":"2026-10-14T07:52:52.161124+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":1293,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik3-retry02-20261014","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik3-retry02-20261014-pack_objects_into_box-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik3-retry02-20261014-pack_objects_into_box-random-s0-scene0.json"},{"created_at":"2026-10-14T07:24:14.208804+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":81,"model_responses":81,"native_controls":725,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik3-retry02-20261014","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik3-retry02-20261014-stack_bowls-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik3-retry02-20261014-stack_bowls-random-s0-scene0.json"},{"created_at":"2026-10-14T07:39:49.282615+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":96,"model_responses":96,"native_controls":666,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik3-retry02-20261014","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik3-retry02-20261014-sweep_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik3-retry02-20261014-sweep_blocks-random-s0-scene0.json"},{"created_at":"2026-10-14T04:45:48.149791+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":185,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-align_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-align_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:07:30.534310+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":80,"model_responses":80,"native_controls":647,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-arrange_largest_number-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-arrange_largest_number-random-s0-scene0.json"},{"created_at":"2026-10-14T04:53:37.380228+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":93,"model_responses":93,"native_controls":945,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-build_tower-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-build_tower-standard-s0-scene0.json"},{"created_at":"2026-10-14T05:16:47.148859+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":78,"model_responses":78,"native_controls":1100,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-classify_objects-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-classify_objects-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:52:15.264618+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":872,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-classify_objects_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-classify_objects_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-14T05:21:02.000313+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":64,"model_responses":64,"native_controls":447,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-cover_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-cover_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:11:53.107830+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":280,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-deposit_coin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-deposit_coin-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:48:01.529363+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":87,"model_responses":87,"native_controls":1070,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-fasten_screws-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-fasten_screws-standard-s0-scene0.json"},{"created_at":"2026-10-14T04:01:46.329815+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":98,"model_responses":98,"native_controls":697,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-fill_egg_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-fill_egg_holder-standard-s0-scene0.json"},{"created_at":"2026-10-14T04:58:44.427216+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":45,"model_responses":45,"native_controls":570,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-fill_pen_holder-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-fill_pen_holder-standard-s0-scene0.json"},{"created_at":"2026-10-13T14:45:44.170081+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":35,"model_responses":35,"native_controls":342,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-fold_clothes-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-fold_clothes-random-s0-scene0.json"},{"created_at":"2026-10-14T05:27:57.316864+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":14,"model_responses":14,"native_controls":94,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-general_pickup-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-general_pickup-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:06:55.765862+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":14,"model_responses":14,"native_controls":240,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-insert_key-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-insert_key-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:41:59.116425+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":466,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-insert_tubes-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-insert_tubes-standard-s0-scene0.json"},{"created_at":"2026-10-14T05:04:10.424175+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":33,"model_responses":33,"native_controls":184,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-make_kong-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-make_kong-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:12:14.221004+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":661,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-make_toast-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-make_toast-random-s0-scene0.json"},{"created_at":"2026-10-14T05:30:46.741602+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":30,"model_responses":30,"native_controls":445,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-match_and_pick_from_conveyor-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-match_and_pick_from_conveyor-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:53:48.979975+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":89,"model_responses":89,"native_controls":825,"native_terminal":true,"score":0.5,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-organize_table-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-organize_table-standard-s0-scene0.json"},{"created_at":"2026-10-14T05:11:51.114070+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":24,"model_responses":24,"native_controls":574,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-pick_from_conveyor_by_image-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-pick_from_conveyor_by_image-standard-s0-scene0.json"},{"created_at":"2026-10-14T04:39:43.291017+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":82,"model_responses":82,"native_controls":479,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-play_Xylophone-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-play_Xylophone-standard-s0-scene0.json"},{"created_at":"2026-10-14T04:12:11.742299+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":100,"model_responses":100,"native_controls":646,"native_terminal":true,"score":0.3,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-play_stacking_toy-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-play_stacking_toy-standard-s0-scene0.json"},{"created_at":"2026-10-14T04:58:11.343985+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":63,"model_responses":63,"native_controls":210,"native_terminal":true,"score":0.1,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-play_tic_tac_toe-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-play_tic_tac_toe-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:42:48.892329+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":591,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-pour_balls_into_vase-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-pour_balls_into_vase-standard-s0-scene0.json"},{"created_at":"2026-10-14T05:20:31.904938+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":780,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-pour_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-pour_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-13T14:41:55.358853+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":21,"model_responses":21,"native_controls":312,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-pour_liquid_into_cup-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-pour_liquid_into_cup-random-s0-scene0.json"},{"created_at":"2026-10-14T04:55:03.687814+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":373,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-press_by_number-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-press_by_number-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:15:44.736650+00:00","episode":{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":38,"model_responses":38,"native_controls":652,"native_terminal":true,"score":0.4,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-put_bottles_into_dustbin-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-put_bottles_into_dustbin-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:09:27.568706+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":25,"model_responses":25,"native_controls":300,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-solve_equation-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-solve_equation-standard-s0-scene0.json"},{"created_at":"2026-10-14T03:47:32.585328+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":70,"model_responses":70,"native_controls":884,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-sort_nesting_dolls_by_size-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-sort_nesting_dolls_by_size-random-s0-scene0.json"},{"created_at":"2026-10-14T02:57:42.630808+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":47,"model_responses":47,"native_controls":396,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-stack_blocks-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-stack_blocks-random-s0-scene0.json"},{"created_at":"2026-10-14T05:43:15.823136+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":36,"model_responses":36,"native_controls":287,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-stack_blocks_by_language-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-stack_blocks_by_language-standard-s0-scene0.json"},{"created_at":"2026-10-14T04:54:23.232123+00:00","episode":{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":94,"model_responses":94,"native_controls":780,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-store_tools_in_toolbox-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-store_tools_in_toolbox-standard-s0-scene0.json"},{"created_at":"2026-10-14T04:39:45.732972+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":37,"model_responses":37,"native_controls":400,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-swap_T-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-swap_T-standard-s0-scene0.json"},{"created_at":"2026-10-14T05:20:27.071578+00:00","episode":{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":700,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik42-medium-20261013-swap_blocks-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik42-medium-20261013-swap_blocks-standard-s0-scene0.json"},{"created_at":"2026-10-14T06:33:17.042857+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":77,"model_responses":77,"native_controls":777,"native_terminal":true,"score":0.15,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik7-retry01-20261014-hang_mugs-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik7-retry01-20261014-hang_mugs-random-s0-scene0.json"},{"created_at":"2026-10-14T06:18:21.168670+00:00","episode":{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":43,"model_responses":43,"native_controls":372,"native_terminal":true,"score":0.0,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik7-retry01-20261014-plug_in_charger-standard-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik7-retry01-20261014-plug_in_charger-standard-s0-scene0.json"},{"created_at":"2026-10-14T06:19:30.319090+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":48,"model_responses":48,"native_controls":408,"native_terminal":true,"score":1.0,"status":"complete","success":true},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik7-retry01-20261014-push_T-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik7-retry01-20261014-push_T-random-s0-scene0.json"},{"created_at":"2026-10-14T06:27:10.141678+00:00","episode":{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},"evidence_level":"native_terminal","formal_episode_result":true,"memberships":[{"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","preserved_unselected":false,"rounds":[1],"selected":true,"selection_id":"persistent-nocap-rerun","supplementary":false}],"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"outcome":{"model_decisions":66,"model_responses":66,"native_controls":627,"native_terminal":true,"score":0.2,"status":"complete","success":false},"protocol":{"id":"thunlp-full-ik42-medium-20261013","max_decisions":100,"native_control_cap":null,"profile":"persistent","score_scale":"0..1"},"run_id":"thunlp-full-ik7-retry01-20261014-store_laptop_and_headphones-random-s0-scene0","url":"https://zefanw.github.io/robodojo-l3-dashboard/api/v1/results/thunlp-full-ik7-retry01-20261014-store_laptop_and_headphones-random-s0-scene0.json"}],"schema_version":"robodojo-api-v1","snapshot_id":"6de891ddca6174e456e977647b6e9fb30ee5587cc8e74659138d072d01a66a0e"}
