{"count":89,"results":[{"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":"2026-10-22T15:14:42.861015+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":"2026-10-22T23:36:01.785638+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":"2026-10-23T04:09:24.862514+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":"2026-10-16T18:58:20.097308+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":"2026-10-16T19:10:01.640597+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":"2026-11-02T16:37:36.290268+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":"2026-10-17T06:00:54.305170+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":"2026-10-15T18:19:53.618836+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":"2026-10-13T07:33:55.508962+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":"2026-10-12T17:04:50.094236+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":"2026-10-13T13:58:45.850837+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":"2026-10-13T16:55:05.488493+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":"2026-10-13T18:21:11.845245+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":"2026-10-15T19:24:46.741208+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":"2026-10-14T23:29:14.869662+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":"2026-10-15T00:49:47.650373+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":"2026-10-15T02:37:47.872163+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":"2026-10-16T10:31:59.754881+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":"2026-10-16T10:24:19.233393+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":"2026-10-17T10:51:30.324654+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":"2026-10-16T04:46:51.764392+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":"2026-10-15T19:58:17.665071+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":"2026-10-18T03:14:07.872673+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":"2026-10-17T07:12:16.945191+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":"2026-10-24T07:03:34.511292+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":"2026-10-19T10:08:10.074869+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":"2026-10-20T11:56:26.160614+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":"2026-10-20T21:26:22.635977+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":"2026-10-23T06:35:25.694510+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":"2026-10-21T10:46:56.979356+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":"2026-10-17T15:02:20.684454+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":"2026-10-23T12:02:55.561716+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":"2026-10-23T19:26:38.596434+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":"2026-10-20T19:54:55.367335+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":"2026-10-23T23:40:45.638398+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":"2026-10-20T06:29:47.972202+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":"2026-10-20T10:16:31.633519+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":"2026-10-05T20:51:52.796573Z","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":"2026-10-08T15:32:59.274929Z","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":"2026-11-02T16:30:49.162297+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":"2026-10-02T05:20:15.077019+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":"2026-11-03T12:51:21.898072+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":"2026-11-04T19:21:49.577671+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":"2026-11-03T16:38:04.508306+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":"2026-11-01T11:23:44.349668+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":"2026-11-05T13:37:15.729388+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":"2026-10-29T09:13:41.037324+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":"2026-10-28T17:58:57.966808+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":"2026-10-27T19:28:07.299611+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":"2026-10-24T22:17:42.576704+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":"2026-11-01T06:23:11.441932+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":"2026-11-01T08:03:46.444788+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":"2026-10-23T11:28:26.522780+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":"2026-11-01T15:47:18.884439+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":"2026-10-20T17:39:31.874910+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":"2026-10-19T16:28:47.361820+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":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":"2026-10-15T16:24:46.842460+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":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"}],"schema_version":"robodojo-api-v1","snapshot_id":"6de891ddca6174e456e977647b6e9fb30ee5587cc8e74659138d072d01a66a0e","task":"imitate_sorting_sequence"}
