{"aggregation":"task_mean_then_capability_mean_then_equal_five_capability_mean","evaluation_plan_sha256":"a1cbdefc2a2ffd4869fee17672a5c91948fdb84f49f6c98782976cae99512389","experiments":[{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4041666666666666,"success_rate":0.3541666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.325,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6041666666666666,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.415625,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.14375000000000002,"success_rate":0.0625}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.37854166666666667,"selected_run_ids":["dual42-horizon-medium-20261016-align_blocks-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene1","dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene2","dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene3","dual42-horizon-medium-20261016-arrange_largest_number-random-s0-scene0","dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene0","dev23-horizon-medium-20261017-arrange_largest_number-random-s0-scene1","dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene1","dual42-horizon-medium-20261016-build_tower-standard-s0-scene0","dual42-horizon-medium-20261016-classify_objects-standard-s0-scene0","dev23-horizon-medium-20261017-classify_objects-standard-s0-scene1","dev23-horizon-medium-20261017-classify_objects-standard-s0-scene2","dev23-horizon-medium-20261017-classify_objects-standard-s0-scene3","dual42-horizon-medium-20261016-classify_objects_by_language-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-classify_objects_by_language-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-classify_objects_by_language-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-classify_objects_by_language-standard-s0-scene3","dual42-horizon-medium-20261016-cover_blocks-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-cover_blocks-standard-s0-scene1","dev23-horizon-medium-20261017-cover_blocks-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-cover_blocks-standard-s0-scene3","dual42-horizon-medium-20261016-deposit_coin-standard-s0-scene0","dual42-horizon-medium-20261016-fasten_screws-standard-s0-scene0","dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene1","dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-fasten_screws-standard-s0-scene3","dual42-horizon-medium-20261016-fill_egg_holder-standard-s0-scene0","dual42-horizon-medium-20261016-fill_pen_holder-standard-s0-scene0","dual42-horizon-medium-20261016-fold_clothes-random-s0-scene0","dev23-horizon-medium-20261017-fold_clothes-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-fold_clothes-random-s0-scene1","dev23-horizon-medium-20261017-p50supp1-fold_clothes-standard-s0-scene1","dual42-horizon-medium-20261016-general_pickup-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-general_pickup-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-general_pickup-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-general_pickup-standard-s0-scene3","dual42-horizon-medium-20261016-hang_mugs-random-s0-scene0","dual42-horizon-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-imitate_sorting_sequence-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene3","dual42-horizon-medium-20261016-insert_key-standard-s0-scene0","dual42-horizon-medium-20261016-insert_tubes-standard-s0-scene0","dual42-horizon-medium-20261016-make_kong-standard-s0-scene0","dual42-horizon-medium-20261016-make_toast-random-s0-scene0","dual42-horizon-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1","dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene2","dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene3","dual42-horizon-medium-20261016-organize_table-standard-s0-scene0","dual42-horizon-medium-20261016-pack_objects_into_box-random-s0-scene0","dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene0","dev23-horizon-medium-20261017-pack_objects_into_box-random-s0-scene1","dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene1","dual42-horizon-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene3","dual42-horizon-medium-20261016-play_Xylophone-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene1","dev23-horizon-medium-20261017-play_Xylophone-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene3","dual42-horizon-medium-20261016-play_stacking_toy-standard-s0-scene0","dual42-horizon-medium-20261016-play_tic_tac_toe-standard-s0-scene0","dual42-horizon-medium-20261016-plug_in_charger-standard-s0-scene0","dev23-horizon-medium-20261017-plug_in_charger-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-plug_in_charger-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-plug_in_charger-standard-s0-scene3","dual42-horizon-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene1","dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene2","dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene3","dual42-horizon-medium-20261016-pour_by_language-standard-s0-scene0","dual42-horizon-medium-20261016-pour_liquid_into_cup-random-s0-scene0","dual42-horizon-medium-20261016-press_by_number-standard-s0-scene0","dev23-horizon-medium-20261017-press_by_number-standard-s0-scene1","dev23-horizon-medium-20261017-press_by_number-standard-s0-scene2","dev23-horizon-medium-20261017-p50supp1-press_by_number-standard-s0-scene3","dual42-horizon-medium-20261016-push_T-random-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-random-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene1","dual42-horizon-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-put_bottles_into_dustbin-standard-s0-scene1","dev23-horizon-medium-20261017-put_bottles_into_dustbin-standard-s0-scene2","dev23-horizon-medium-20261017-put_bottles_into_dustbin-standard-s0-scene3","dual42-horizon-medium-20261016-solve_equation-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene3","dual42-horizon-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-sort_nesting_dolls_by_size-standard-s0-scene0","dev23-horizon-medium-20261017-sort_nesting_dolls_by_size-random-s0-scene1","dev23-horizon-medium-20261017-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene1","dual42-horizon-medium-20261016-stack_blocks-random-s0-scene0","dual42-horizon-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene3","dual42-horizon-medium-20261016-stack_bowls-random-s0-scene0","dev23-horizon-medium-20261017-p50supp1-stack_bowls-standard-s0-scene0","dev23-horizon-medium-20261017-stack_bowls-random-s0-scene1","dev23-horizon-medium-20261017-stack_bowls-standard-s0-scene1","dual42-horizon-medium-20261016-store_laptop_and_headphones-random-s0-scene0","dual42-horizon-medium-20261016-store_tools_in_toolbox-standard-s0-scene0","dual42-horizon-medium-20261016-swap_T-standard-s0-scene0","dev23-horizon-medium-20261017-swap_T-standard-s0-scene1","dev23-horizon-medium-20261017-swap_T-standard-s0-scene2","dev23-horizon-medium-20261017-swap_T-standard-s0-scene3","dual42-horizon-medium-20261016-swap_blocks-standard-s0-scene0","dual42-horizon-medium-20261016-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-align_blocks-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene1","dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene2","dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-arrange_largest_number-random-s0-scene0","dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene0","dev23-horizon-medium-20261017-arrange_largest_number-random-s0-scene1","dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene1"],"score":0.675,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-classify_objects-standard-s0-scene0","dev23-horizon-medium-20261017-classify_objects-standard-s0-scene1","dev23-horizon-medium-20261017-classify_objects-standard-s0-scene2","dev23-horizon-medium-20261017-classify_objects-standard-s0-scene3"],"score":0.7875,"success_rate":0.75,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-classify_objects_by_language-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-classify_objects_by_language-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-classify_objects_by_language-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-classify_objects_by_language-standard-s0-scene3"],"score":0.325,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-cover_blocks-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-cover_blocks-standard-s0-scene1","dev23-horizon-medium-20261017-cover_blocks-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-cover_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-fasten_screws-standard-s0-scene0","dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene1","dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-fasten_screws-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-fold_clothes-random-s0-scene0","dev23-horizon-medium-20261017-fold_clothes-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-fold_clothes-random-s0-scene1","dev23-horizon-medium-20261017-p50supp1-fold_clothes-standard-s0-scene1"],"score":0.8,"success_rate":0.75,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-general_pickup-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-general_pickup-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-general_pickup-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-imitate_sorting_sequence-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene3"],"score":0.875,"success_rate":0.75,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1","dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene2","dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-pack_objects_into_box-random-s0-scene0","dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene0","dev23-horizon-medium-20261017-pack_objects_into_box-random-s0-scene1","dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene1"],"score":0.4375,"success_rate":0.25,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-play_Xylophone-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene1","dev23-horizon-medium-20261017-play_Xylophone-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-plug_in_charger-standard-s0-scene0","dev23-horizon-medium-20261017-plug_in_charger-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-plug_in_charger-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-plug_in_charger-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene1","dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene2","dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-press_by_number-standard-s0-scene0","dev23-horizon-medium-20261017-press_by_number-standard-s0-scene1","dev23-horizon-medium-20261017-press_by_number-standard-s0-scene2","dev23-horizon-medium-20261017-p50supp1-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-push_T-random-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-random-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-put_bottles_into_dustbin-standard-s0-scene1","dev23-horizon-medium-20261017-put_bottles_into_dustbin-standard-s0-scene2","dev23-horizon-medium-20261017-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.5125,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-solve_equation-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-sort_nesting_dolls_by_size-standard-s0-scene0","dev23-horizon-medium-20261017-sort_nesting_dolls_by_size-random-s0-scene1","dev23-horizon-medium-20261017-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene1","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene2","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-stack_bowls-random-s0-scene0","dev23-horizon-medium-20261017-p50supp1-stack_bowls-standard-s0-scene0","dev23-horizon-medium-20261017-stack_bowls-random-s0-scene1","dev23-horizon-medium-20261017-stack_bowls-standard-s0-scene1"],"score":0.5375,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-horizon-medium-20261016-swap_T-standard-s0-scene0","dev23-horizon-medium-20261017-swap_T-standard-s0-scene1","dev23-horizon-medium-20261017-swap_T-standard-s0-scene2","dev23-horizon-medium-20261017-swap_T-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.5125000000000001,"success_rate":0.5},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.31875,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.55,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.10625,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.43083333333333335,"selected_run_ids":["dual42-horizon-medium-20261016-align_blocks-standard-s0-scene0","dual42-horizon-medium-20261016-arrange_largest_number-random-s0-scene0","dual42-horizon-medium-20261016-build_tower-standard-s0-scene0","dual42-horizon-medium-20261016-classify_objects-standard-s0-scene0","dual42-horizon-medium-20261016-classify_objects_by_language-standard-s0-scene0","dual42-horizon-medium-20261016-cover_blocks-standard-s0-scene0","dual42-horizon-medium-20261016-deposit_coin-standard-s0-scene0","dual42-horizon-medium-20261016-fasten_screws-standard-s0-scene0","dual42-horizon-medium-20261016-fill_egg_holder-standard-s0-scene0","dual42-horizon-medium-20261016-fill_pen_holder-standard-s0-scene0","dual42-horizon-medium-20261016-fold_clothes-random-s0-scene0","dual42-horizon-medium-20261016-general_pickup-standard-s0-scene0","dual42-horizon-medium-20261016-hang_mugs-random-s0-scene0","dual42-horizon-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dual42-horizon-medium-20261016-insert_key-standard-s0-scene0","dual42-horizon-medium-20261016-insert_tubes-standard-s0-scene0","dual42-horizon-medium-20261016-make_kong-standard-s0-scene0","dual42-horizon-medium-20261016-make_toast-random-s0-scene0","dual42-horizon-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dual42-horizon-medium-20261016-organize_table-standard-s0-scene0","dual42-horizon-medium-20261016-pack_objects_into_box-random-s0-scene0","dual42-horizon-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dual42-horizon-medium-20261016-play_Xylophone-standard-s0-scene0","dual42-horizon-medium-20261016-play_stacking_toy-standard-s0-scene0","dual42-horizon-medium-20261016-play_tic_tac_toe-standard-s0-scene0","dual42-horizon-medium-20261016-plug_in_charger-standard-s0-scene0","dual42-horizon-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dual42-horizon-medium-20261016-pour_by_language-standard-s0-scene0","dual42-horizon-medium-20261016-pour_liquid_into_cup-random-s0-scene0","dual42-horizon-medium-20261016-press_by_number-standard-s0-scene0","dual42-horizon-medium-20261016-push_T-random-s0-scene0","dual42-horizon-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dual42-horizon-medium-20261016-solve_equation-standard-s0-scene0","dual42-horizon-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dual42-horizon-medium-20261016-stack_blocks-random-s0-scene0","dual42-horizon-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dual42-horizon-medium-20261016-stack_bowls-random-s0-scene0","dual42-horizon-medium-20261016-store_laptop_and_headphones-random-s0-scene0","dual42-horizon-medium-20261016-store_tools_in_toolbox-standard-s0-scene0","dual42-horizon-medium-20261016-swap_T-standard-s0-scene0","dual42-horizon-medium-20261016-swap_blocks-standard-s0-scene0","dual42-horizon-medium-20261016-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3583333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-fasten_screws-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pack_objects_into_box-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4583333333333333,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.365625,"success_rate":0.1875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5833333333333334,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.4875,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.15,"success_rate":0.0625}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.40895833333333337,"selected_run_ids":["dual42-horizon-medium-20261016-align_blocks-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene1","dual42-horizon-medium-20261016-arrange_largest_number-random-s0-scene0","dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene0","dual42-horizon-medium-20261016-build_tower-standard-s0-scene0","dual42-horizon-medium-20261016-classify_objects-standard-s0-scene0","dev23-horizon-medium-20261017-classify_objects-standard-s0-scene1","dual42-horizon-medium-20261016-classify_objects_by_language-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-classify_objects_by_language-standard-s0-scene1","dual42-horizon-medium-20261016-cover_blocks-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-cover_blocks-standard-s0-scene1","dual42-horizon-medium-20261016-deposit_coin-standard-s0-scene0","dual42-horizon-medium-20261016-fasten_screws-standard-s0-scene0","dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene1","dual42-horizon-medium-20261016-fill_egg_holder-standard-s0-scene0","dual42-horizon-medium-20261016-fill_pen_holder-standard-s0-scene0","dual42-horizon-medium-20261016-fold_clothes-random-s0-scene0","dev23-horizon-medium-20261017-fold_clothes-standard-s0-scene0","dual42-horizon-medium-20261016-general_pickup-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-general_pickup-standard-s0-scene1","dual42-horizon-medium-20261016-hang_mugs-random-s0-scene0","dual42-horizon-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene1","dual42-horizon-medium-20261016-insert_key-standard-s0-scene0","dual42-horizon-medium-20261016-insert_tubes-standard-s0-scene0","dual42-horizon-medium-20261016-make_kong-standard-s0-scene0","dual42-horizon-medium-20261016-make_toast-random-s0-scene0","dual42-horizon-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1","dual42-horizon-medium-20261016-organize_table-standard-s0-scene0","dual42-horizon-medium-20261016-pack_objects_into_box-random-s0-scene0","dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene0","dual42-horizon-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene1","dual42-horizon-medium-20261016-play_Xylophone-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene1","dual42-horizon-medium-20261016-play_stacking_toy-standard-s0-scene0","dual42-horizon-medium-20261016-play_tic_tac_toe-standard-s0-scene0","dual42-horizon-medium-20261016-plug_in_charger-standard-s0-scene0","dev23-horizon-medium-20261017-plug_in_charger-standard-s0-scene1","dual42-horizon-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene1","dual42-horizon-medium-20261016-pour_by_language-standard-s0-scene0","dual42-horizon-medium-20261016-pour_liquid_into_cup-random-s0-scene0","dual42-horizon-medium-20261016-press_by_number-standard-s0-scene0","dev23-horizon-medium-20261017-press_by_number-standard-s0-scene1","dual42-horizon-medium-20261016-push_T-random-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene0","dual42-horizon-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-put_bottles_into_dustbin-standard-s0-scene1","dual42-horizon-medium-20261016-solve_equation-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene1","dual42-horizon-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-sort_nesting_dolls_by_size-standard-s0-scene0","dual42-horizon-medium-20261016-stack_blocks-random-s0-scene0","dual42-horizon-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene1","dual42-horizon-medium-20261016-stack_bowls-random-s0-scene0","dev23-horizon-medium-20261017-p50supp1-stack_bowls-standard-s0-scene0","dual42-horizon-medium-20261016-store_laptop_and_headphones-random-s0-scene0","dual42-horizon-medium-20261016-store_tools_in_toolbox-standard-s0-scene0","dual42-horizon-medium-20261016-swap_T-standard-s0-scene0","dev23-horizon-medium-20261017-swap_T-standard-s0-scene1","dual42-horizon-medium-20261016-swap_blocks-standard-s0-scene0","dual42-horizon-medium-20261016-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3375,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-align_blocks-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-arrange_largest_number-random-s0-scene0","dev23-horizon-medium-20261017-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-classify_objects-standard-s0-scene0","dev23-horizon-medium-20261017-classify_objects-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-classify_objects_by_language-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-classify_objects_by_language-standard-s0-scene1"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-cover_blocks-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-fasten_screws-standard-s0-scene0","dev23-horizon-medium-20261017-fasten_screws-standard-s0-scene1"],"score":0.35,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-fold_clothes-random-s0-scene0","dev23-horizon-medium-20261017-fold_clothes-standard-s0-scene0"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-general_pickup-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-imitate_sorting_sequence-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dev23-horizon-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-pack_objects_into_box-random-s0-scene0","dev23-horizon-medium-20261017-pack_objects_into_box-standard-s0-scene0"],"score":0.75,"success_rate":0.5,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-play_Xylophone-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-plug_in_charger-standard-s0-scene0","dev23-horizon-medium-20261017-plug_in_charger-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dev23-horizon-medium-20261017-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-press_by_number-standard-s0-scene0","dev23-horizon-medium-20261017-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-push_T-random-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dev23-horizon-medium-20261017-p50supp1-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.625,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-solve_equation-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dev23-horizon-medium-20261022-p50supp1-rerun27-retry1-stack_blocks_by_language-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-stack_bowls-random-s0-scene0","dev23-horizon-medium-20261017-p50supp1-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-horizon-medium-20261016-swap_T-standard-s0-scene0","dev23-horizon-medium-20261017-swap_T-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-horizon-medium-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"7064caaf52577dc977d95312266373bef7a90c32ac00d223c36b2f2fe4ed4036","name":"custom-model-action-horizon","selection_id":"dual42-horizon-medium-20261016"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4395833333333334,"success_rate":0.3958333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.4046875,"success_rate":0.09375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5833333333333334,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.471875,"success_rate":0.40625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.2,"success_rate":0.0625}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.41989583333333336,"selected_run_ids":["dual42-sequence-medium-20261016-align_blocks-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene3","dual42-sequence-medium-20261016-arrange_largest_number-random-s0-scene0","dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene0","dev23-sequence-medium-20261017-arrange_largest_number-random-s0-scene1","dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene1","dual42-sequence-medium-20261016-build_tower-standard-s0-scene0","dual42-sequence-medium-20261016-classify_objects-standard-s0-scene0","dev23-sequence-medium-20261017-classify_objects-standard-s0-scene1","dev23-sequence-medium-20261017-classify_objects-standard-s0-scene2","dev23-sequence-medium-20261017-classify_objects-standard-s0-scene3","dual42-sequence-medium-20261016-classify_objects_by_language-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene3","dual42-sequence-medium-20261016-cover_blocks-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene3","dual42-sequence-medium-20261016-deposit_coin-standard-s0-scene0","dual42-sequence-medium-20261016-fasten_screws-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene3","dual42-sequence-medium-20261016-fill_egg_holder-standard-s0-scene0","dual42-sequence-medium-20261016-fill_pen_holder-standard-s0-scene0","dual42-sequence-medium-20261016-fold_clothes-random-s0-scene0","dev23-sequence-medium-20261017-fold_clothes-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-fold_clothes-random-s0-scene1","dev23-sequence-medium-20261023-p50supp1-fold_clothes-standard-s0-scene1","dual42-sequence-medium-20261016-general_pickup-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene3","dual42-sequence-medium-20261016-hang_mugs-random-s0-scene0","dual42-sequence-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene3","dual42-sequence-medium-20261016-insert_key-standard-s0-scene0","dual42-sequence-medium-20261016-insert_tubes-standard-s0-scene0","dual42-sequence-medium-20261016-make_kong-standard-s0-scene0","dual42-sequence-medium-20261016-make_toast-random-s0-scene0","dual42-sequence-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1","dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene2","dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene3","dual42-sequence-medium-20261016-organize_table-standard-s0-scene0","dual42-sequence-medium-20261016-pack_objects_into_box-random-s0-scene0","dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene0","dev23-sequence-medium-20261017-pack_objects_into_box-random-s0-scene1","dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene1","dual42-sequence-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene3","dual42-sequence-medium-20261016-play_Xylophone-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene3","dual42-sequence-medium-20261016-play_stacking_toy-standard-s0-scene0","dual42-sequence-medium-20261016-play_tic_tac_toe-standard-s0-scene0","dual42-sequence-medium-20261016-plug_in_charger-standard-s0-scene0","dev23-sequence-medium-20261017-plug_in_charger-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-plug_in_charger-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-plug_in_charger-standard-s0-scene3","dual42-sequence-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene1","dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene2","dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene3","dual42-sequence-medium-20261016-pour_by_language-standard-s0-scene0","dual42-sequence-medium-20261016-pour_liquid_into_cup-random-s0-scene0","dual42-sequence-medium-20261016-press_by_number-standard-s0-scene0","dev23-sequence-medium-20261017-press_by_number-standard-s0-scene1","dev23-sequence-medium-20261017-press_by_number-standard-s0-scene2","dev23-sequence-medium-20261017-press_by_number-standard-s0-scene3","dual42-sequence-medium-20261016-push_T-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene0","dev23-sequence-medium-20261017-push_T-random-s0-scene1","dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene1","dual42-sequence-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-put_bottles_into_dustbin-standard-s0-scene2","dev23-sequence-medium-20261017-put_bottles_into_dustbin-standard-s0-scene3","dual42-sequence-medium-20261016-solve_equation-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene3","dual42-sequence-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-random-s0-scene1","dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene1","dual42-sequence-medium-20261016-stack_blocks-random-s0-scene0","dual42-sequence-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene3","dual42-sequence-medium-20261016-stack_bowls-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-stack_bowls-standard-s0-scene0","dev23-sequence-medium-20261017-stack_bowls-random-s0-scene1","dev23-sequence-medium-20261017-stack_bowls-standard-s0-scene1","dual42-sequence-medium-20261016-store_laptop_and_headphones-random-s0-scene0","dual42-sequence-medium-20261016-store_tools_in_toolbox-standard-s0-scene0","dual42-sequence-medium-20261016-swap_T-standard-s0-scene0","dev23-sequence-medium-20261017-swap_T-standard-s0-scene1","dev23-sequence-medium-20261017-swap_T-standard-s0-scene2","dev23-sequence-medium-20261017-swap_T-standard-s0-scene3","dual42-sequence-medium-20261016-swap_blocks-standard-s0-scene0","dual42-sequence-medium-20261016-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.30833333333333335,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-align_blocks-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-arrange_largest_number-random-s0-scene0","dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene0","dev23-sequence-medium-20261017-arrange_largest_number-random-s0-scene1","dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene1"],"score":0.675,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-classify_objects-standard-s0-scene0","dev23-sequence-medium-20261017-classify_objects-standard-s0-scene1","dev23-sequence-medium-20261017-classify_objects-standard-s0-scene2","dev23-sequence-medium-20261017-classify_objects-standard-s0-scene3"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-classify_objects_by_language-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene3"],"score":0.47500000000000003,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-cover_blocks-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-fasten_screws-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene3"],"score":0.5,"success_rate":0.25,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-fold_clothes-random-s0-scene0","dev23-sequence-medium-20261017-fold_clothes-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-fold_clothes-random-s0-scene1","dev23-sequence-medium-20261023-p50supp1-fold_clothes-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-general_pickup-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1","dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene2","dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-pack_objects_into_box-random-s0-scene0","dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene0","dev23-sequence-medium-20261017-pack_objects_into_box-random-s0-scene1","dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene1"],"score":0.275,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-play_Xylophone-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-plug_in_charger-standard-s0-scene0","dev23-sequence-medium-20261017-plug_in_charger-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-plug_in_charger-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene1","dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene2","dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-press_by_number-standard-s0-scene0","dev23-sequence-medium-20261017-press_by_number-standard-s0-scene1","dev23-sequence-medium-20261017-press_by_number-standard-s0-scene2","dev23-sequence-medium-20261017-press_by_number-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-push_T-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene0","dev23-sequence-medium-20261017-push_T-random-s0-scene1","dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-put_bottles_into_dustbin-standard-s0-scene2","dev23-sequence-medium-20261017-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.4375,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-solve_equation-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-random-s0-scene1","dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene1","dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene2","dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene3"],"score":0.8,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-stack_bowls-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-stack_bowls-standard-s0-scene0","dev23-sequence-medium-20261017-stack_bowls-random-s0-scene1","dev23-sequence-medium-20261017-stack_bowls-standard-s0-scene1"],"score":0.575,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["dual42-sequence-medium-20261016-swap_T-standard-s0-scene0","dev23-sequence-medium-20261017-swap_T-standard-s0-scene1","dev23-sequence-medium-20261017-swap_T-standard-s0-scene2","dev23-sequence-medium-20261017-swap_T-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.37916666666666665,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.34375,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.65625,"success_rate":0.625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.16875,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.4429166666666666,"selected_run_ids":["dual42-sequence-medium-20261016-align_blocks-standard-s0-scene0","dual42-sequence-medium-20261016-arrange_largest_number-random-s0-scene0","dual42-sequence-medium-20261016-build_tower-standard-s0-scene0","dual42-sequence-medium-20261016-classify_objects-standard-s0-scene0","dual42-sequence-medium-20261016-classify_objects_by_language-standard-s0-scene0","dual42-sequence-medium-20261016-cover_blocks-standard-s0-scene0","dual42-sequence-medium-20261016-deposit_coin-standard-s0-scene0","dual42-sequence-medium-20261016-fasten_screws-standard-s0-scene0","dual42-sequence-medium-20261016-fill_egg_holder-standard-s0-scene0","dual42-sequence-medium-20261016-fill_pen_holder-standard-s0-scene0","dual42-sequence-medium-20261016-fold_clothes-random-s0-scene0","dual42-sequence-medium-20261016-general_pickup-standard-s0-scene0","dual42-sequence-medium-20261016-hang_mugs-random-s0-scene0","dual42-sequence-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dual42-sequence-medium-20261016-insert_key-standard-s0-scene0","dual42-sequence-medium-20261016-insert_tubes-standard-s0-scene0","dual42-sequence-medium-20261016-make_kong-standard-s0-scene0","dual42-sequence-medium-20261016-make_toast-random-s0-scene0","dual42-sequence-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dual42-sequence-medium-20261016-organize_table-standard-s0-scene0","dual42-sequence-medium-20261016-pack_objects_into_box-random-s0-scene0","dual42-sequence-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dual42-sequence-medium-20261016-play_Xylophone-standard-s0-scene0","dual42-sequence-medium-20261016-play_stacking_toy-standard-s0-scene0","dual42-sequence-medium-20261016-play_tic_tac_toe-standard-s0-scene0","dual42-sequence-medium-20261016-plug_in_charger-standard-s0-scene0","dual42-sequence-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dual42-sequence-medium-20261016-pour_by_language-standard-s0-scene0","dual42-sequence-medium-20261016-pour_liquid_into_cup-random-s0-scene0","dual42-sequence-medium-20261016-press_by_number-standard-s0-scene0","dual42-sequence-medium-20261016-push_T-random-s0-scene0","dual42-sequence-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dual42-sequence-medium-20261016-solve_equation-standard-s0-scene0","dual42-sequence-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dual42-sequence-medium-20261016-stack_blocks-random-s0-scene0","dual42-sequence-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dual42-sequence-medium-20261016-stack_bowls-random-s0-scene0","dual42-sequence-medium-20261016-store_laptop_and_headphones-random-s0-scene0","dual42-sequence-medium-20261016-store_tools_in_toolbox-standard-s0-scene0","dual42-sequence-medium-20261016-swap_T-standard-s0-scene0","dual42-sequence-medium-20261016-swap_blocks-standard-s0-scene0","dual42-sequence-medium-20261016-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.325,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-arrange_largest_number-random-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-fasten_screws-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pack_objects_into_box-random-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4083333333333334,"success_rate":0.375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.428125,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5833333333333334,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.50625,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.1375,"success_rate":0.0}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.41270833333333334,"selected_run_ids":["dual42-sequence-medium-20261016-align_blocks-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene1","dual42-sequence-medium-20261016-arrange_largest_number-random-s0-scene0","dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene0","dual42-sequence-medium-20261016-build_tower-standard-s0-scene0","dual42-sequence-medium-20261016-classify_objects-standard-s0-scene0","dev23-sequence-medium-20261017-classify_objects-standard-s0-scene1","dual42-sequence-medium-20261016-classify_objects_by_language-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene1","dual42-sequence-medium-20261016-cover_blocks-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene1","dual42-sequence-medium-20261016-deposit_coin-standard-s0-scene0","dual42-sequence-medium-20261016-fasten_screws-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene1","dual42-sequence-medium-20261016-fill_egg_holder-standard-s0-scene0","dual42-sequence-medium-20261016-fill_pen_holder-standard-s0-scene0","dual42-sequence-medium-20261016-fold_clothes-random-s0-scene0","dev23-sequence-medium-20261017-fold_clothes-standard-s0-scene0","dual42-sequence-medium-20261016-general_pickup-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene1","dual42-sequence-medium-20261016-hang_mugs-random-s0-scene0","dual42-sequence-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene1","dual42-sequence-medium-20261016-insert_key-standard-s0-scene0","dual42-sequence-medium-20261016-insert_tubes-standard-s0-scene0","dual42-sequence-medium-20261016-make_kong-standard-s0-scene0","dual42-sequence-medium-20261016-make_toast-random-s0-scene0","dual42-sequence-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1","dual42-sequence-medium-20261016-organize_table-standard-s0-scene0","dual42-sequence-medium-20261016-pack_objects_into_box-random-s0-scene0","dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene0","dual42-sequence-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1","dual42-sequence-medium-20261016-play_Xylophone-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene1","dual42-sequence-medium-20261016-play_stacking_toy-standard-s0-scene0","dual42-sequence-medium-20261016-play_tic_tac_toe-standard-s0-scene0","dual42-sequence-medium-20261016-plug_in_charger-standard-s0-scene0","dev23-sequence-medium-20261017-plug_in_charger-standard-s0-scene1","dual42-sequence-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene1","dual42-sequence-medium-20261016-pour_by_language-standard-s0-scene0","dual42-sequence-medium-20261016-pour_liquid_into_cup-random-s0-scene0","dual42-sequence-medium-20261016-press_by_number-standard-s0-scene0","dev23-sequence-medium-20261017-press_by_number-standard-s0-scene1","dual42-sequence-medium-20261016-push_T-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene0","dual42-sequence-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene1","dual42-sequence-medium-20261016-solve_equation-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene1","dual42-sequence-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0","dual42-sequence-medium-20261016-stack_blocks-random-s0-scene0","dual42-sequence-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene1","dual42-sequence-medium-20261016-stack_bowls-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-stack_bowls-standard-s0-scene0","dual42-sequence-medium-20261016-store_laptop_and_headphones-random-s0-scene0","dual42-sequence-medium-20261016-store_tools_in_toolbox-standard-s0-scene0","dual42-sequence-medium-20261016-swap_T-standard-s0-scene0","dev23-sequence-medium-20261017-swap_T-standard-s0-scene1","dual42-sequence-medium-20261016-swap_blocks-standard-s0-scene0","dual42-sequence-medium-20261016-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3041666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-align_blocks-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-arrange_largest_number-random-s0-scene0","dev23-sequence-medium-20261017-arrange_largest_number-standard-s0-scene0"],"score":0.65,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-classify_objects-standard-s0-scene0","dev23-sequence-medium-20261017-classify_objects-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-classify_objects_by_language-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-classify_objects_by_language-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-cover_blocks-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-fasten_screws-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-fasten_screws-standard-s0-scene1"],"score":0.25,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-fold_clothes-random-s0-scene0","dev23-sequence-medium-20261017-fold_clothes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-general_pickup-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-imitate_sorting_sequence-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-imitate_sorting_sequence-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-match_and_pick_from_conveyor-standard-s0-scene0","dev23-sequence-medium-20261017-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-pack_objects_into_box-random-s0-scene0","dev23-sequence-medium-20261017-pack_objects_into_box-standard-s0-scene0"],"score":0.175,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-pick_from_conveyor_by_image-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-play_Xylophone-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-plug_in_charger-standard-s0-scene0","dev23-sequence-medium-20261017-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-pour_balls_into_vase-standard-s0-scene0","dev23-sequence-medium-20261017-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-press_by_number-standard-s0-scene0","dev23-sequence-medium-20261017-press_by_number-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-push_T-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-put_bottles_into_dustbin-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.625,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-solve_equation-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-sort_nesting_dolls_by_size-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-stack_blocks_by_language-standard-s0-scene0","dev23-sequence-medium-20261023-p50supp1-stack_blocks_by_language-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-stack_bowls-random-s0-scene0","dev23-sequence-medium-20261023-p50supp1-stack_bowls-standard-s0-scene0"],"score":0.575,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["dual42-sequence-medium-20261016-swap_T-standard-s0-scene0","dev23-sequence-medium-20261017-swap_T-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["dual42-sequence-medium-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"4b91ccaca40fece9834bee45d233aca8c52c4ff5b128bf1c05a1a9ef4dc9d16f","name":"dual42-sequence-medium-20261016","selection_id":"dual42-sequence-medium-20261016"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.2708333333333333,"success_rate":0.25},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2796875,"success_rate":0.09375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5666666666666667,"success_rate":0.5416666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.46875,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.109375,"success_rate":0.03125}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.3390625,"selected_run_ids":["l3-eef-relative-cap20-medium-r1-20261015-align_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-align_blocks-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-align_blocks-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-align_blocks-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-arrange_largest_number-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-build_tower-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-classify_objects-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-restart1-20261017-classify_objects-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-classify_objects_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-cover_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-deposit_coin-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fasten_screws-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-fill_egg_holder-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fill_pen_holder-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fold_clothes-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-general_pickup-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-hang_mugs-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-imitate_sorting_sequence-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-insert_key-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-insert_tubes-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-make_kong-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-make_toast-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-match_and_pick_from_conveyor-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-match_and_pick_from_conveyor-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-organize_table-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pack_objects_into_box-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-pick_from_conveyor_by_image-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-play_Xylophone-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-play_stacking_toy-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-play_tic_tac_toe-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-plug_in_charger-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-pour_balls_into_vase-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-pour_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pour_liquid_into_cup-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-press_by_number-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-push_T-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-push_T-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-push_T-random-s0-scene1","l3-eef-relative-cap20-medium-devset-restart1-20261017-push_T-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-put_bottles_into_dustbin-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-solve_equation-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-sort_nesting_dolls_by_size-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-sort_nesting_dolls_by_size-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-stack_blocks-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-stack_blocks_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-stack_bowls-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-store_laptop_and_headphones-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-store_tools_in_toolbox-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-swap_T-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene3","l3-eef-relative-cap20-medium-r1-20261015-swap_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2708333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-align_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-align_blocks-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-align_blocks-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-align_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-arrange_largest_number-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene1"],"score":0.825,"success_rate":0.75,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-classify_objects-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-restart1-20261017-classify_objects-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene3"],"score":0.6375,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-classify_objects_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene3"],"score":0.45,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-cover_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene3"],"score":0.575,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fasten_screws-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene3"],"score":0.425,"success_rate":0.25,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fold_clothes-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene1"],"score":0.8,"success_rate":0.75,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-general_pickup-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-imitate_sorting_sequence-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene3"],"score":0.575,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-match_and_pick_from_conveyor-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-match_and_pick_from_conveyor-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pack_objects_into_box-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene1"],"score":0.0875,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pick_from_conveyor_by_image-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_Xylophone-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-plug_in_charger-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_balls_into_vase-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-press_by_number-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-push_T-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-push_T-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-push_T-random-s0-scene1","l3-eef-relative-cap20-medium-devset-restart1-20261017-push_T-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-put_bottles_into_dustbin-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-solve_equation-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-sort_nesting_dolls_by_size-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-sort_nesting_dolls_by_size-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_blocks_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene3"],"score":0.55,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_bowls-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-random-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene1"],"score":0.5375,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-swap_T-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene1","l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene2","l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.29583333333333334,"success_rate":0.25},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.30625,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.5,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.18125,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.3566666666666667,"selected_run_ids":["l3-eef-relative-cap20-medium-r1-20261015-align_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-arrange_largest_number-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-build_tower-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-classify_objects-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-classify_objects_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-cover_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-deposit_coin-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fasten_screws-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fill_egg_holder-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fill_pen_holder-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fold_clothes-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-general_pickup-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-hang_mugs-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-imitate_sorting_sequence-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-insert_key-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-insert_tubes-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-make_kong-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-make_toast-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-match_and_pick_from_conveyor-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-organize_table-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pack_objects_into_box-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pick_from_conveyor_by_image-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-play_Xylophone-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-play_stacking_toy-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-play_tic_tac_toe-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-plug_in_charger-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pour_balls_into_vase-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pour_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pour_liquid_into_cup-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-press_by_number-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-push_T-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-put_bottles_into_dustbin-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-solve_equation-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-sort_nesting_dolls_by_size-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-stack_blocks-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-stack_blocks_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-stack_bowls-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-store_laptop_and_headphones-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-store_tools_in_toolbox-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-swap_T-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-swap_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-arrange_largest_number-random-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fasten_screws-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-imitate_sorting_sequence-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pack_objects_into_box-random-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.3145833333333333,"success_rate":0.2916666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.29062499999999997,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.525,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.4625,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.15,"success_rate":0.0625}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.34854166666666664,"selected_run_ids":["l3-eef-relative-cap20-medium-r1-20261015-align_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-align_blocks-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-arrange_largest_number-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-build_tower-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-classify_objects-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-classify_objects_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-cover_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-deposit_coin-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fasten_screws-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-fill_egg_holder-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fill_pen_holder-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-fold_clothes-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-general_pickup-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-hang_mugs-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-imitate_sorting_sequence-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-insert_key-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-insert_tubes-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-make_kong-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-make_toast-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-match_and_pick_from_conveyor-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-organize_table-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pack_objects_into_box-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pick_from_conveyor_by_image-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-play_Xylophone-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-play_stacking_toy-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-play_tic_tac_toe-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-plug_in_charger-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-pour_balls_into_vase-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-pour_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-pour_liquid_into_cup-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-press_by_number-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-push_T-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-push_T-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-put_bottles_into_dustbin-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-solve_equation-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-sort_nesting_dolls_by_size-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-stack_blocks-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-stack_blocks_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-stack_bowls-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-store_laptop_and_headphones-random-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-store_tools_in_toolbox-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-swap_T-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene1","l3-eef-relative-cap20-medium-r1-20261015-swap_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-r1-20261015-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2833333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-align_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-align_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-arrange_largest_number-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-arrange_largest_number-standard-s0-scene0"],"score":0.65,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-classify_objects-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-classify_objects-standard-s0-scene1"],"score":0.575,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-classify_objects_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-classify_objects_by_language-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-cover_blocks-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-cover_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fasten_screws-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fasten_screws-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-fold_clothes-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-fold_clothes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-general_pickup-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-imitate_sorting_sequence-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-imitate_sorting_sequence-standard-s0-scene1"],"score":0.15,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-match_and_pick_from_conveyor-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-restart1-20261017-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pack_objects_into_box-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pack_objects_into_box-standard-s0-scene0"],"score":0.125,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pick_from_conveyor_by_image-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_Xylophone-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-plug_in_charger-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_balls_into_vase-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-press_by_number-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-push_T-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-push_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-put_bottles_into_dustbin-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-solve_equation-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-solve_equation-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-sort_nesting_dolls_by_size-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_blocks_by_language-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_blocks_by_language-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-stack_bowls-random-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-swap_T-standard-s0-scene0","l3-eef-relative-cap20-medium-devset-20261017-swap_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-eef-relative-cap20-medium-r1-20261015-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"48915f9ccae2d5b8846ebcb2924f5720ea9896b8224ab04f6977dcbd5f948a69","name":"persistent-cap20-eef-relative","selection_id":"l3-eef-relative-cap20-medium-r1-20261015"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.3833333333333333,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2375,"success_rate":0.09375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6729166666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.40625,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.171875,"success_rate":0.0625}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.374375,"selected_run_ids":["l3-high-mixed42-20261013-align_blocks-standard-s0-scene0","high-dev69-20261102-align_blocks-standard-s0-scene1","high-dev69-20261102-align_blocks-standard-s0-scene2","high-dev69-20261102-align_blocks-standard-s0-scene3","l3-high-mixed42-20261013-arrange_largest_number-random-s0-scene0","high-dev69-20261102-arrange_largest_number-standard-s0-scene0","high-dev69-20261102-arrange_largest_number-random-s0-scene1","high-dev69-20261102-arrange_largest_number-standard-s0-scene1","l3-high-mixed42-20261013-build_tower-standard-s0-scene0","l3-high-mixed42-20261013-classify_objects-standard-s0-scene0","high-dev69-20261102-classify_objects-standard-s0-scene1","high-dev69-20261102-classify_objects-standard-s0-scene2","high-dev69-20261102-classify_objects-standard-s0-scene3","l3-high-mixed42-20261013-classify_objects_by_language-standard-s0-scene0","high-dev69-20261102-classify_objects_by_language-standard-s0-scene1","high-dev69-20261102-classify_objects_by_language-standard-s0-scene2","high-dev69-20261102-classify_objects_by_language-standard-s0-scene3","l3-high-mixed42-20261013-cover_blocks-standard-s0-scene0","high-dev69-20261102-cover_blocks-standard-s0-scene1","high-dev69-20261102-cover_blocks-standard-s0-scene2","high-dev69-20261102-cover_blocks-standard-s0-scene3","l3-high-mixed42-20261013-deposit_coin-standard-s0-scene0","l3-high-mixed42-20261013-fasten_screws-standard-s0-scene0","high-dev69-20261102-fasten_screws-standard-s0-scene1","high-dev69-20261102-fasten_screws-standard-s0-scene2","high-dev69-20261102-fasten_screws-standard-s0-scene3","l3-high-mixed42-20261013-fill_egg_holder-standard-s0-scene0","l3-high-mixed42-20261013-fill_pen_holder-standard-s0-scene0","l3-high-mixed42-20261013-fold_clothes-random-s0-scene0","high-dev69-20261102-fold_clothes-standard-s0-scene0","high-dev69-20261102-fold_clothes-random-s0-scene1","high-dev69-20261102-fold_clothes-standard-s0-scene1","l3-high-mixed42-20261013-general_pickup-standard-s0-scene0","high-dev69-20261102-general_pickup-standard-s0-scene1","high-dev69-20261102-general_pickup-standard-s0-scene2","high-dev69-20261102-general_pickup-standard-s0-scene3","l3-high-mixed42-20261013-hang_mugs-random-s0-scene0","l3-high-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene0","high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene1","high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene2","high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene3","l3-high-mixed42-20261013-insert_key-standard-s0-scene0","l3-high-mixed42-20261013-insert_tubes-standard-s0-scene0","l3-high-mixed42-20261013-make_kong-standard-s0-scene0","l3-high-mixed42-20261013-make_toast-random-s0-scene0","l3-high-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene0","high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene1","high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene2","high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene3","l3-high-mixed42-20261013-organize_table-standard-s0-scene0","l3-high-mixed42-20261013-pack_objects_into_box-random-s0-scene0","high-dev69-20261102-pack_objects_into_box-standard-s0-scene0","high-dev69-20261102-pack_objects_into_box-random-s0-scene1","high-dev69-20261102-pack_objects_into_box-standard-s0-scene1","l3-high-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene0","high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene1","high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene2","high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene3","l3-high-mixed42-20261013-play_Xylophone-standard-s0-scene0","high-dev69-20261102-play_Xylophone-standard-s0-scene1","high-dev69-20261102-play_Xylophone-standard-s0-scene2","high-dev69-20261102-play_Xylophone-standard-s0-scene3","l3-high-mixed42-20261013-play_stacking_toy-standard-s0-scene0","l3-high-mixed42-20261013-play_tic_tac_toe-standard-s0-scene0","l3-high-mixed42-20261013-plug_in_charger-standard-s0-scene0","high-dev69-20261102-plug_in_charger-standard-s0-scene1","high-dev69-20261102-plug_in_charger-standard-s0-scene2","high-dev69-20261102-plug_in_charger-standard-s0-scene3","l3-high-mixed42-20261013-pour_balls_into_vase-standard-s0-scene0","high-dev69-20261102-pour_balls_into_vase-standard-s0-scene1","high-dev69-20261102-pour_balls_into_vase-standard-s0-scene2","high-dev69-20261102-pour_balls_into_vase-standard-s0-scene3","l3-high-mixed42-20261013-pour_by_language-standard-s0-scene0","l3-high-mixed42-20261013-pour_liquid_into_cup-random-s0-scene0","l3-high-mixed42-20261013-press_by_number-standard-s0-scene0","high-dev69-20261102-press_by_number-standard-s0-scene1","high-dev69-20261102-press_by_number-standard-s0-scene2","high-dev69-20261102-press_by_number-standard-s0-scene3","l3-high-mixed42-20261013-push_T-random-s0-scene0","high-dev69-20261102-push_T-standard-s0-scene0","high-dev69-20261102-push_T-random-s0-scene1","high-dev69-20261102-push_T-standard-s0-scene1","l3-high-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene0","high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1","high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene2","high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene3","l3-high-mixed42-20261013-solve_equation-standard-s0-scene0","high-dev69-20261102-solve_equation-standard-s0-scene1","high-dev69-20261102-solve_equation-standard-s0-scene2","high-dev69-20261102-solve_equation-standard-s0-scene3","l3-high-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene0","high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0","high-dev69-20261102-sort_nesting_dolls_by_size-random-s0-scene1","high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene1","l3-high-mixed42-20261013-stack_blocks-random-s0-scene0","l3-high-mixed42-20261013-stack_blocks_by_language-standard-s0-scene0","high-dev69-20261102-stack_blocks_by_language-standard-s0-scene1","high-dev69-20261102-stack_blocks_by_language-standard-s0-scene2","high-dev69-20261102-stack_blocks_by_language-standard-s0-scene3","l3-high-mixed42-20261013-stack_bowls-random-s0-scene0","high-dev69-20261102-stack_bowls-standard-s0-scene0","high-dev69-20261102-stack_bowls-random-s0-scene1","high-dev69-20261102-stack_bowls-standard-s0-scene1","l3-high-mixed42-20261013-store_laptop_and_headphones-random-s0-scene0","l3-high-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene0","l3-high-mixed42-20261013-swap_T-standard-s0-scene0","high-dev69-20261102-swap_T-standard-s0-scene1","high-dev69-20261102-swap_T-standard-s0-scene2","high-dev69-20261102-swap_T-standard-s0-scene3","l3-high-mixed42-20261013-swap_blocks-standard-s0-scene0","l3-high-mixed42-20261013-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.30625,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-align_blocks-standard-s0-scene0","high-dev69-20261102-align_blocks-standard-s0-scene1","high-dev69-20261102-align_blocks-standard-s0-scene2","high-dev69-20261102-align_blocks-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-arrange_largest_number-random-s0-scene0","high-dev69-20261102-arrange_largest_number-standard-s0-scene0","high-dev69-20261102-arrange_largest_number-random-s0-scene1","high-dev69-20261102-arrange_largest_number-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-classify_objects-standard-s0-scene0","high-dev69-20261102-classify_objects-standard-s0-scene1","high-dev69-20261102-classify_objects-standard-s0-scene2","high-dev69-20261102-classify_objects-standard-s0-scene3"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-classify_objects_by_language-standard-s0-scene0","high-dev69-20261102-classify_objects_by_language-standard-s0-scene1","high-dev69-20261102-classify_objects_by_language-standard-s0-scene2","high-dev69-20261102-classify_objects_by_language-standard-s0-scene3"],"score":0.45,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-cover_blocks-standard-s0-scene0","high-dev69-20261102-cover_blocks-standard-s0-scene1","high-dev69-20261102-cover_blocks-standard-s0-scene2","high-dev69-20261102-cover_blocks-standard-s0-scene3"],"score":0.7875,"success_rate":0.75,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-fasten_screws-standard-s0-scene0","high-dev69-20261102-fasten_screws-standard-s0-scene1","high-dev69-20261102-fasten_screws-standard-s0-scene2","high-dev69-20261102-fasten_screws-standard-s0-scene3"],"score":0.225,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-fold_clothes-random-s0-scene0","high-dev69-20261102-fold_clothes-standard-s0-scene0","high-dev69-20261102-fold_clothes-random-s0-scene1","high-dev69-20261102-fold_clothes-standard-s0-scene1"],"score":0.8,"success_rate":0.75,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-general_pickup-standard-s0-scene0","high-dev69-20261102-general_pickup-standard-s0-scene1","high-dev69-20261102-general_pickup-standard-s0-scene2","high-dev69-20261102-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene0","high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene1","high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene2","high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene0","high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene1","high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene2","high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-pack_objects_into_box-random-s0-scene0","high-dev69-20261102-pack_objects_into_box-standard-s0-scene0","high-dev69-20261102-pack_objects_into_box-random-s0-scene1","high-dev69-20261102-pack_objects_into_box-standard-s0-scene1"],"score":0.2125,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene0","high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene1","high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene2","high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-play_Xylophone-standard-s0-scene0","high-dev69-20261102-play_Xylophone-standard-s0-scene1","high-dev69-20261102-play_Xylophone-standard-s0-scene2","high-dev69-20261102-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-plug_in_charger-standard-s0-scene0","high-dev69-20261102-plug_in_charger-standard-s0-scene1","high-dev69-20261102-plug_in_charger-standard-s0-scene2","high-dev69-20261102-plug_in_charger-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-pour_balls_into_vase-standard-s0-scene0","high-dev69-20261102-pour_balls_into_vase-standard-s0-scene1","high-dev69-20261102-pour_balls_into_vase-standard-s0-scene2","high-dev69-20261102-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-press_by_number-standard-s0-scene0","high-dev69-20261102-press_by_number-standard-s0-scene1","high-dev69-20261102-press_by_number-standard-s0-scene2","high-dev69-20261102-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-push_T-random-s0-scene0","high-dev69-20261102-push_T-standard-s0-scene0","high-dev69-20261102-push_T-random-s0-scene1","high-dev69-20261102-push_T-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene0","high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1","high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene2","high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-solve_equation-standard-s0-scene0","high-dev69-20261102-solve_equation-standard-s0-scene1","high-dev69-20261102-solve_equation-standard-s0-scene2","high-dev69-20261102-solve_equation-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene0","high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0","high-dev69-20261102-sort_nesting_dolls_by_size-random-s0-scene1","high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-stack_blocks_by_language-standard-s0-scene0","high-dev69-20261102-stack_blocks_by_language-standard-s0-scene1","high-dev69-20261102-stack_blocks_by_language-standard-s0-scene2","high-dev69-20261102-stack_blocks_by_language-standard-s0-scene3"],"score":0.8,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-stack_bowls-random-s0-scene0","high-dev69-20261102-stack_bowls-standard-s0-scene0","high-dev69-20261102-stack_bowls-random-s0-scene1","high-dev69-20261102-stack_bowls-standard-s0-scene1"],"score":0.7875,"success_rate":0.75,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-high-mixed42-20261013-swap_T-standard-s0-scene0","high-dev69-20261102-swap_T-standard-s0-scene1","high-dev69-20261102-swap_T-standard-s0-scene2","high-dev69-20261102-swap_T-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.3625,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.18125,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.425,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.26875,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.3808333333333333,"selected_run_ids":["l3-high-mixed42-20261013-align_blocks-standard-s0-scene0","l3-high-mixed42-20261013-arrange_largest_number-random-s0-scene0","l3-high-mixed42-20261013-build_tower-standard-s0-scene0","l3-high-mixed42-20261013-classify_objects-standard-s0-scene0","l3-high-mixed42-20261013-classify_objects_by_language-standard-s0-scene0","l3-high-mixed42-20261013-cover_blocks-standard-s0-scene0","l3-high-mixed42-20261013-deposit_coin-standard-s0-scene0","l3-high-mixed42-20261013-fasten_screws-standard-s0-scene0","l3-high-mixed42-20261013-fill_egg_holder-standard-s0-scene0","l3-high-mixed42-20261013-fill_pen_holder-standard-s0-scene0","l3-high-mixed42-20261013-fold_clothes-random-s0-scene0","l3-high-mixed42-20261013-general_pickup-standard-s0-scene0","l3-high-mixed42-20261013-hang_mugs-random-s0-scene0","l3-high-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene0","l3-high-mixed42-20261013-insert_key-standard-s0-scene0","l3-high-mixed42-20261013-insert_tubes-standard-s0-scene0","l3-high-mixed42-20261013-make_kong-standard-s0-scene0","l3-high-mixed42-20261013-make_toast-random-s0-scene0","l3-high-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene0","l3-high-mixed42-20261013-organize_table-standard-s0-scene0","l3-high-mixed42-20261013-pack_objects_into_box-random-s0-scene0","l3-high-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene0","l3-high-mixed42-20261013-play_Xylophone-standard-s0-scene0","l3-high-mixed42-20261013-play_stacking_toy-standard-s0-scene0","l3-high-mixed42-20261013-play_tic_tac_toe-standard-s0-scene0","l3-high-mixed42-20261013-plug_in_charger-standard-s0-scene0","l3-high-mixed42-20261013-pour_balls_into_vase-standard-s0-scene0","l3-high-mixed42-20261013-pour_by_language-standard-s0-scene0","l3-high-mixed42-20261013-pour_liquid_into_cup-random-s0-scene0","l3-high-mixed42-20261013-press_by_number-standard-s0-scene0","l3-high-mixed42-20261013-push_T-random-s0-scene0","l3-high-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene0","l3-high-mixed42-20261013-solve_equation-standard-s0-scene0","l3-high-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene0","l3-high-mixed42-20261013-stack_blocks-random-s0-scene0","l3-high-mixed42-20261013-stack_blocks_by_language-standard-s0-scene0","l3-high-mixed42-20261013-stack_bowls-random-s0-scene0","l3-high-mixed42-20261013-store_laptop_and_headphones-random-s0-scene0","l3-high-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene0","l3-high-mixed42-20261013-swap_T-standard-s0-scene0","l3-high-mixed42-20261013-swap_blocks-standard-s0-scene0","l3-high-mixed42-20261013-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-arrange_largest_number-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-fasten_screws-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pack_objects_into_box-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-plug_in_charger-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.41875,"success_rate":0.375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.21875,"success_rate":0.0625},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5833333333333334,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.35,"success_rate":0.3125},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.175,"success_rate":0.0625}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.3491666666666667,"selected_run_ids":["l3-high-mixed42-20261013-align_blocks-standard-s0-scene0","high-dev69-20261102-align_blocks-standard-s0-scene1","l3-high-mixed42-20261013-arrange_largest_number-random-s0-scene0","high-dev69-20261102-arrange_largest_number-standard-s0-scene0","l3-high-mixed42-20261013-build_tower-standard-s0-scene0","l3-high-mixed42-20261013-classify_objects-standard-s0-scene0","high-dev69-20261102-classify_objects-standard-s0-scene1","l3-high-mixed42-20261013-classify_objects_by_language-standard-s0-scene0","high-dev69-20261102-classify_objects_by_language-standard-s0-scene1","l3-high-mixed42-20261013-cover_blocks-standard-s0-scene0","high-dev69-20261102-cover_blocks-standard-s0-scene1","l3-high-mixed42-20261013-deposit_coin-standard-s0-scene0","l3-high-mixed42-20261013-fasten_screws-standard-s0-scene0","high-dev69-20261102-fasten_screws-standard-s0-scene1","l3-high-mixed42-20261013-fill_egg_holder-standard-s0-scene0","l3-high-mixed42-20261013-fill_pen_holder-standard-s0-scene0","l3-high-mixed42-20261013-fold_clothes-random-s0-scene0","high-dev69-20261102-fold_clothes-standard-s0-scene0","l3-high-mixed42-20261013-general_pickup-standard-s0-scene0","high-dev69-20261102-general_pickup-standard-s0-scene1","l3-high-mixed42-20261013-hang_mugs-random-s0-scene0","l3-high-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene0","high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene1","l3-high-mixed42-20261013-insert_key-standard-s0-scene0","l3-high-mixed42-20261013-insert_tubes-standard-s0-scene0","l3-high-mixed42-20261013-make_kong-standard-s0-scene0","l3-high-mixed42-20261013-make_toast-random-s0-scene0","l3-high-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene0","high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene1","l3-high-mixed42-20261013-organize_table-standard-s0-scene0","l3-high-mixed42-20261013-pack_objects_into_box-random-s0-scene0","high-dev69-20261102-pack_objects_into_box-standard-s0-scene0","l3-high-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene0","high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene1","l3-high-mixed42-20261013-play_Xylophone-standard-s0-scene0","high-dev69-20261102-play_Xylophone-standard-s0-scene1","l3-high-mixed42-20261013-play_stacking_toy-standard-s0-scene0","l3-high-mixed42-20261013-play_tic_tac_toe-standard-s0-scene0","l3-high-mixed42-20261013-plug_in_charger-standard-s0-scene0","high-dev69-20261102-plug_in_charger-standard-s0-scene1","l3-high-mixed42-20261013-pour_balls_into_vase-standard-s0-scene0","high-dev69-20261102-pour_balls_into_vase-standard-s0-scene1","l3-high-mixed42-20261013-pour_by_language-standard-s0-scene0","l3-high-mixed42-20261013-pour_liquid_into_cup-random-s0-scene0","l3-high-mixed42-20261013-press_by_number-standard-s0-scene0","high-dev69-20261102-press_by_number-standard-s0-scene1","l3-high-mixed42-20261013-push_T-random-s0-scene0","high-dev69-20261102-push_T-standard-s0-scene0","l3-high-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene0","high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1","l3-high-mixed42-20261013-solve_equation-standard-s0-scene0","high-dev69-20261102-solve_equation-standard-s0-scene1","l3-high-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene0","high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0","l3-high-mixed42-20261013-stack_blocks-random-s0-scene0","l3-high-mixed42-20261013-stack_blocks_by_language-standard-s0-scene0","high-dev69-20261102-stack_blocks_by_language-standard-s0-scene1","l3-high-mixed42-20261013-stack_bowls-random-s0-scene0","high-dev69-20261102-stack_bowls-standard-s0-scene0","l3-high-mixed42-20261013-store_laptop_and_headphones-random-s0-scene0","l3-high-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene0","l3-high-mixed42-20261013-swap_T-standard-s0-scene0","high-dev69-20261102-swap_T-standard-s0-scene1","l3-high-mixed42-20261013-swap_blocks-standard-s0-scene0","l3-high-mixed42-20261013-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2791666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-align_blocks-standard-s0-scene0","high-dev69-20261102-align_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-arrange_largest_number-random-s0-scene0","high-dev69-20261102-arrange_largest_number-standard-s0-scene0"],"score":0.575,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-classify_objects-standard-s0-scene0","high-dev69-20261102-classify_objects-standard-s0-scene1"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-classify_objects_by_language-standard-s0-scene0","high-dev69-20261102-classify_objects_by_language-standard-s0-scene1"],"score":0.2,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-cover_blocks-standard-s0-scene0","high-dev69-20261102-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-fasten_screws-standard-s0-scene0","high-dev69-20261102-fasten_screws-standard-s0-scene1"],"score":0.25,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-fold_clothes-random-s0-scene0","high-dev69-20261102-fold_clothes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-general_pickup-standard-s0-scene0","high-dev69-20261102-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene0","high-dev69-20261102-imitate_sorting_sequence-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene0","high-dev69-20261102-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-pack_objects_into_box-random-s0-scene0","high-dev69-20261102-pack_objects_into_box-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene0","high-dev69-20261102-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-play_Xylophone-standard-s0-scene0","high-dev69-20261102-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-plug_in_charger-standard-s0-scene0","high-dev69-20261102-plug_in_charger-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-pour_balls_into_vase-standard-s0-scene0","high-dev69-20261102-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-press_by_number-standard-s0-scene0","high-dev69-20261102-press_by_number-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-push_T-random-s0-scene0","high-dev69-20261102-push_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene0","high-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-solve_equation-standard-s0-scene0","high-dev69-20261102-solve_equation-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene0","high-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-stack_blocks_by_language-standard-s0-scene0","high-dev69-20261102-stack_blocks_by_language-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-stack_bowls-random-s0-scene0","high-dev69-20261102-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-high-mixed42-20261013-swap_T-standard-s0-scene0","high-dev69-20261102-swap_T-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-high-mixed42-20261013-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"c102dd0549fbb6e86066eadad087d76bc9a603aafe396f9cbd924ba56870eaed","name":"l3-high-mixed42-20261013","selection_id":"l3-high-mixed42-20261013"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":41,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-luna-cap20-medium-r1-20261016-align_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-arrange_largest_number-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-build_tower-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-classify_objects-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-cover_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-deposit_coin-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fasten_screws-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fill_egg_holder-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fill_pen_holder-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fold_clothes-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-general_pickup-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-hang_mugs-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-imitate_sorting_sequence-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-insert_key-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-insert_tubes-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-make_kong-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-make_toast-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-organize_table-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pack_objects_into_box-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-pick_from_conveyor_by_image-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_Xylophone-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_stacking_toy-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-plug_in_charger-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-pour_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-press_by_number-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-push_T-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-solve_equation-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-stack_blocks-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-swap_T-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-supplement84-swap_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-insert_key-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-organize_table-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-cap20-medium-r1-20261016-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-supplement84-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":11,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.0,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.0,"success_rate":0.0},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.0,"success_rate":0.0},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.0,"success_rate":0.0}},"completed":41,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["l3-luna-cap20-medium-r1-20261016-align_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-arrange_largest_number-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-build_tower-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-classify_objects-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-cover_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-deposit_coin-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fasten_screws-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fill_egg_holder-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fill_pen_holder-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fold_clothes-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-general_pickup-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-hang_mugs-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-imitate_sorting_sequence-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-insert_key-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-insert_tubes-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-make_kong-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-make_toast-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-organize_table-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pack_objects_into_box-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-pick_from_conveyor_by_image-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_Xylophone-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_stacking_toy-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-plug_in_charger-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-pour_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-press_by_number-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-push_T-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-solve_equation-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-stack_blocks-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-swap_T-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-supplement84-swap_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-arrange_largest_number-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-classify_objects-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-cover_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-fasten_screws-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-fold_clothes-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-general_pickup-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-imitate_sorting_sequence-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-insert_key-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-organize_table-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-pack_objects_into_box-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-press_by_number-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-supplement84-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":41,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-luna-cap20-medium-r1-20261016-align_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-arrange_largest_number-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-build_tower-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-classify_objects-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-cover_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-deposit_coin-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fasten_screws-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fill_egg_holder-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fill_pen_holder-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-fold_clothes-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-general_pickup-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-hang_mugs-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-imitate_sorting_sequence-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-insert_key-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-insert_tubes-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-make_kong-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-make_toast-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-organize_table-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pack_objects_into_box-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-pick_from_conveyor_by_image-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_Xylophone-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_stacking_toy-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-plug_in_charger-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-rerun1650-pour_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-press_by_number-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-push_T-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-solve_equation-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-stack_blocks-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0","l3-luna-cap20-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-swap_T-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-supplement84-swap_blocks-standard-s0-scene0","l3-luna-cap20-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-insert_key-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-organize_table-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-rerun1650-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-cap20-medium-r1-20261016-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-supplement84-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-cap20-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"57b651f1c3517242d42491a2ef4e27f122305c71fe6b9177dc34d4dc66701b28","name":"l3-luna-cap20-medium-r1-20261016","selection_id":"l3-luna-cap20-medium-r1-20261016"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-luna-nocap-medium-r1-20261016-align_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-arrange_largest_number-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-build_tower-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-classify_objects-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-cover_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-deposit_coin-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fasten_screws-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fill_egg_holder-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fill_pen_holder-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fold_clothes-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-general_pickup-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-hang_mugs-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-supplement84-imitate_sorting_sequence-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-insert_key-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-insert_tubes-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-make_kong-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-make_toast-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-organize_table-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pack_objects_into_box-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-pick_from_conveyor_by_image-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_Xylophone-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_stacking_toy-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-plug_in_charger-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-press_by_number-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-push_T-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-solve_equation-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_blocks-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_bowls-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-swap_T-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-swap_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-supplement84-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-insert_key-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-organize_table-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-luna-nocap-medium-r1-20261016-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.0,"success_rate":0.0},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.0,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.0,"success_rate":0.0},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.0,"success_rate":0.0},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.0,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.0,"selected_run_ids":["l3-luna-nocap-medium-r1-20261016-align_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-arrange_largest_number-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-build_tower-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-classify_objects-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-cover_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-deposit_coin-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fasten_screws-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fill_egg_holder-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fill_pen_holder-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fold_clothes-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-general_pickup-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-hang_mugs-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-supplement84-imitate_sorting_sequence-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-insert_key-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-insert_tubes-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-make_kong-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-make_toast-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-organize_table-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pack_objects_into_box-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-pick_from_conveyor_by_image-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_Xylophone-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_stacking_toy-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-plug_in_charger-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-press_by_number-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-push_T-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-solve_equation-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_blocks-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_bowls-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-swap_T-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-swap_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.0,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-arrange_largest_number-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-classify_objects-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-cover_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-fasten_screws-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-fold_clothes-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-general_pickup-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-supplement84-imitate_sorting_sequence-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-insert_key-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-organize_table-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pack_objects_into_box-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-press_by_number-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_bowls-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-luna-nocap-medium-r1-20261016-align_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-arrange_largest_number-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-build_tower-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-classify_objects-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-cover_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-deposit_coin-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fasten_screws-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fill_egg_holder-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fill_pen_holder-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-fold_clothes-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-general_pickup-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-hang_mugs-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-supplement84-imitate_sorting_sequence-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-insert_key-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-insert_tubes-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-make_kong-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-make_toast-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-organize_table-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pack_objects_into_box-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-pick_from_conveyor_by_image-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_Xylophone-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_stacking_toy-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-plug_in_charger-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-press_by_number-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-push_T-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-solve_equation-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_blocks-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-stack_bowls-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0","l3-luna-nocap-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-swap_T-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-swap_blocks-standard-s0-scene0","l3-luna-nocap-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-supplement84-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-insert_key-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-organize_table-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-luna-nocap-medium-r1-20261016-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-luna-nocap-medium-r1-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"90f3528c216724e5be85cb4e69d955fe407ca879d798ce4c3fa26f487b5a4450","name":"l3-luna-nocap-medium-r1-20261016","selection_id":"l3-luna-nocap-medium-r1-20261016"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4083333333333334,"success_rate":0.3541666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.275,"success_rate":0.15625},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6458333333333334,"success_rate":0.625},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.465625,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.196875,"success_rate":0.09375}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.3983333333333333,"selected_run_ids":["l3-o1-compact-precision4-20261017-v1-align_blocks-standard-s0-scene0","l3-o1compact-devset-20261024-align_blocks-standard-s0-scene1","l3-o1compact-devset-20261024-align_blocks-standard-s0-scene2","l3-o1compact-devset-20261024-align_blocks-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-arrange_largest_number-random-s0-scene0","l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene0","l3-o1compact-devset-20261024-arrange_largest_number-random-s0-scene1","l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-build_tower-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-classify_objects-standard-s0-scene0","l3-o1compact-devset-20261024-classify_objects-standard-s0-scene1","l3-o1compact-devset-20261024-classify_objects-standard-s0-scene2","l3-o1compact-devset-20261024-classify_objects-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-classify_objects_by_language-standard-s0-scene0","l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene1","l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene2","l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-cover_blocks-standard-s0-scene0","l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene1","l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene2","l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fasten_screws-standard-s0-scene0","l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene1","l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene2","l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-fill_egg_holder-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fill_pen_holder-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fold_clothes-random-s0-scene0","l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene0","l3-o1compact-devset-20261024-fold_clothes-random-s0-scene1","l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-general_pickup-standard-s0-scene0","l3-o1compact-devset-20261024-general_pickup-standard-s0-scene1","l3-o1compact-devset-20261024-general_pickup-standard-s0-scene2","l3-o1compact-devset-20261024-general_pickup-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-hang_mugs-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-imitate_sorting_sequence-standard-s0-scene0","l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene1","l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene2","l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-make_kong-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-make_toast-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene1","l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene2","l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-organize_table-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pack_objects_into_box-random-s0-scene0","l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene0","l3-o1compact-devset-20261024-pack_objects_into_box-random-s0-scene1","l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-pick_from_conveyor_by_image-standard-s0-scene0","l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene1","l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene2","l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-play_Xylophone-standard-s0-scene0","l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene1","l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene2","l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-play_stacking_toy-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-play_tic_tac_toe-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene1","l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene2","l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-pour_balls_into_vase-standard-s0-scene0","l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene1","l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene2","l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-pour_by_language-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pour_liquid_into_cup-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-press_by_number-standard-s0-scene0","l3-o1compact-devset-20261024-press_by_number-standard-s0-scene1","l3-o1compact-devset-20261024-press_by_number-standard-s0-scene2","l3-o1compact-devset-20261024-press_by_number-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-push_T-random-s0-scene0","l3-o1compact-devset-20261024-push_T-standard-s0-scene0","l3-o1compact-devset-20261024-push_T-random-s0-scene1","l3-o1compact-devset-20261024-push_T-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene1","l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene2","l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-solve_equation-standard-s0-scene0","l3-o1compact-devset-20261024-solve_equation-standard-s0-scene1","l3-o1compact-devset-20261024-solve_equation-standard-s0-scene2","l3-o1compact-devset-20261024-solve_equation-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-random-s0-scene1","l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-stack_blocks-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-stack_blocks_by_language-standard-s0-scene0","l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene1","l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene2","l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-stack_bowls-random-s0-scene0","l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene0","l3-o1compact-devset-20261024-stack_bowls-random-s0-scene1","l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-store_laptop_and_headphones-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-store_tools_in_toolbox-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-swap_T-standard-s0-scene0","l3-o1compact-devset-20261024-swap_T-standard-s0-scene1","l3-o1compact-devset-20261024-swap_T-standard-s0-scene2","l3-o1compact-devset-20261024-swap_T-standard-s0-scene3","l3-o1-compact-precision4-20261017-v1-swap_blocks-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.33333333333333337,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-align_blocks-standard-s0-scene0","l3-o1compact-devset-20261024-align_blocks-standard-s0-scene1","l3-o1compact-devset-20261024-align_blocks-standard-s0-scene2","l3-o1compact-devset-20261024-align_blocks-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-arrange_largest_number-random-s0-scene0","l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene0","l3-o1compact-devset-20261024-arrange_largest_number-random-s0-scene1","l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene1"],"score":0.675,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-classify_objects-standard-s0-scene0","l3-o1compact-devset-20261024-classify_objects-standard-s0-scene1","l3-o1compact-devset-20261024-classify_objects-standard-s0-scene2","l3-o1compact-devset-20261024-classify_objects-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-classify_objects_by_language-standard-s0-scene0","l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene1","l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene2","l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene3"],"score":0.47500000000000003,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-cover_blocks-standard-s0-scene0","l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene1","l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene2","l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-fasten_screws-standard-s0-scene0","l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene1","l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene2","l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene3"],"score":0.625,"success_rate":0.25,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-fold_clothes-random-s0-scene0","l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene0","l3-o1compact-devset-20261024-fold_clothes-random-s0-scene1","l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene1"],"score":0.8,"success_rate":0.75,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-general_pickup-standard-s0-scene0","l3-o1compact-devset-20261024-general_pickup-standard-s0-scene1","l3-o1compact-devset-20261024-general_pickup-standard-s0-scene2","l3-o1compact-devset-20261024-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-imitate_sorting_sequence-standard-s0-scene0","l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene1","l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene2","l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene3"],"score":0.875,"success_rate":0.75,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene1","l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene2","l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-pack_objects_into_box-random-s0-scene0","l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene0","l3-o1compact-devset-20261024-pack_objects_into_box-random-s0-scene1","l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene1"],"score":0.275,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-pick_from_conveyor_by_image-standard-s0-scene0","l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene1","l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene2","l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_Xylophone-standard-s0-scene0","l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene1","l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene2","l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene1","l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene2","l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_balls_into_vase-standard-s0-scene0","l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene1","l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene2","l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-press_by_number-standard-s0-scene0","l3-o1compact-devset-20261024-press_by_number-standard-s0-scene1","l3-o1compact-devset-20261024-press_by_number-standard-s0-scene2","l3-o1compact-devset-20261024-press_by_number-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-push_T-random-s0-scene0","l3-o1compact-devset-20261024-push_T-standard-s0-scene0","l3-o1compact-devset-20261024-push_T-random-s0-scene1","l3-o1compact-devset-20261024-push_T-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene1","l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene2","l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-solve_equation-standard-s0-scene0","l3-o1compact-devset-20261024-solve_equation-standard-s0-scene1","l3-o1compact-devset-20261024-solve_equation-standard-s0-scene2","l3-o1compact-devset-20261024-solve_equation-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-random-s0-scene1","l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_blocks_by_language-standard-s0-scene0","l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene1","l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene2","l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_bowls-random-s0-scene0","l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene0","l3-o1compact-devset-20261024-stack_bowls-random-s0-scene1","l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o1-compact-precision4-20261017-v1-swap_T-standard-s0-scene0","l3-o1compact-devset-20261024-swap_T-standard-s0-scene1","l3-o1compact-devset-20261024-swap_T-standard-s0-scene2","l3-o1compact-devset-20261024-swap_T-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.3125,"success_rate":0.25},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.25625,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.375,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.30625,"success_rate":0.25}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.3833333333333333,"selected_run_ids":["l3-o1-compact-precision4-20261017-v1-align_blocks-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-arrange_largest_number-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-build_tower-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-classify_objects-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-classify_objects_by_language-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-cover_blocks-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fasten_screws-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fill_egg_holder-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fill_pen_holder-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fold_clothes-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-general_pickup-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-hang_mugs-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-imitate_sorting_sequence-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-make_kong-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-make_toast-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-organize_table-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pack_objects_into_box-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-pick_from_conveyor_by_image-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-play_Xylophone-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-play_stacking_toy-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-play_tic_tac_toe-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pour_balls_into_vase-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pour_by_language-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pour_liquid_into_cup-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-press_by_number-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-push_T-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-solve_equation-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-stack_blocks-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-stack_blocks_by_language-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-stack_bowls-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-store_laptop_and_headphones-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-store_tools_in_toolbox-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-swap_T-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-swap_blocks-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3333333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-arrange_largest_number-random-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-fasten_screws-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pack_objects_into_box-random-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_Xylophone-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.38125000000000003,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.29375,"success_rate":0.1875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.4,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.2125,"success_rate":0.125}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.3908333333333333,"selected_run_ids":["l3-o1-compact-precision4-20261017-v1-align_blocks-standard-s0-scene0","l3-o1compact-devset-20261024-align_blocks-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-arrange_largest_number-random-s0-scene0","l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-build_tower-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-classify_objects-standard-s0-scene0","l3-o1compact-devset-20261024-classify_objects-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-classify_objects_by_language-standard-s0-scene0","l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-cover_blocks-standard-s0-scene0","l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fasten_screws-standard-s0-scene0","l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-fill_egg_holder-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fill_pen_holder-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-fold_clothes-random-s0-scene0","l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-general_pickup-standard-s0-scene0","l3-o1compact-devset-20261024-general_pickup-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-hang_mugs-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-imitate_sorting_sequence-standard-s0-scene0","l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-make_kong-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-make_toast-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-organize_table-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pack_objects_into_box-random-s0-scene0","l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pick_from_conveyor_by_image-standard-s0-scene0","l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-play_Xylophone-standard-s0-scene0","l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-play_stacking_toy-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-play_tic_tac_toe-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-pour_balls_into_vase-standard-s0-scene0","l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-pour_by_language-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-pour_liquid_into_cup-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-press_by_number-standard-s0-scene0","l3-o1compact-devset-20261024-press_by_number-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-push_T-random-s0-scene0","l3-o1compact-devset-20261024-push_T-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-solve_equation-standard-s0-scene0","l3-o1compact-devset-20261024-solve_equation-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-stack_blocks-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-stack_blocks_by_language-standard-s0-scene0","l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-stack_bowls-random-s0-scene0","l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-store_laptop_and_headphones-random-s0-scene0","l3-o1-compact-precision4-20261017-v1-store_tools_in_toolbox-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-swap_T-standard-s0-scene0","l3-o1compact-devset-20261024-swap_T-standard-s0-scene1","l3-o1-compact-precision4-20261017-v1-swap_blocks-standard-s0-scene0","l3-o1-compact-precision4-20261017-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3375,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-align_blocks-standard-s0-scene0","l3-o1compact-devset-20261024-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-arrange_largest_number-random-s0-scene0","l3-o1compact-devset-20261024-arrange_largest_number-standard-s0-scene0"],"score":0.65,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-classify_objects-standard-s0-scene0","l3-o1compact-devset-20261024-classify_objects-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-classify_objects_by_language-standard-s0-scene0","l3-o1compact-devset-20261024-classify_objects_by_language-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-cover_blocks-standard-s0-scene0","l3-o1compact-devset-20261024-cover_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-fasten_screws-standard-s0-scene0","l3-o1compact-devset-20261024-fasten_screws-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-fold_clothes-random-s0-scene0","l3-o1compact-devset-20261024-fold_clothes-standard-s0-scene0"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-general_pickup-standard-s0-scene0","l3-o1compact-devset-20261024-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-imitate_sorting_sequence-standard-s0-scene0","l3-o1compact-devset-20261024-imitate_sorting_sequence-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-o1compact-devset-20261024-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-pack_objects_into_box-random-s0-scene0","l3-o1compact-devset-20261024-pack_objects_into_box-standard-s0-scene0"],"score":0.175,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-pick_from_conveyor_by_image-standard-s0-scene0","l3-o1compact-devset-20261024-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_Xylophone-standard-s0-scene0","l3-o1compact-devset-20261024-play_Xylophone-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o1compact-devset-20261024-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_balls_into_vase-standard-s0-scene0","l3-o1compact-devset-20261024-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-press_by_number-standard-s0-scene0","l3-o1compact-devset-20261024-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-push_T-random-s0-scene0","l3-o1compact-devset-20261024-push_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-o1compact-devset-20261024-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-solve_equation-standard-s0-scene0","l3-o1compact-devset-20261024-solve_equation-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o1compact-devset-20261024-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_blocks_by_language-standard-s0-scene0","l3-o1compact-devset-20261024-stack_blocks_by_language-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-stack_bowls-random-s0-scene0","l3-o1compact-devset-20261024-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o1-compact-precision4-20261017-v1-swap_T-standard-s0-scene0","l3-o1compact-devset-20261024-swap_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-compact-precision4-20261017-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"a914bee7842dceb173378f5813a0cacd00c2a80a696f195588f8259d2bc8f628","name":"O1 compact · medium · R1","selection_id":"l3-o1-compact-precision4-20261017-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-o1-r1-mixed42-20261016-align_blocks-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-arrange_largest_number-random-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-build_tower-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-classify_objects-standard-s0-scene0","l3-o1-r1-mixed42-20261016-classify_objects_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-cover_blocks-standard-s0-scene0","l3-o1-precision4-20261016-v1-deposit_coin-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fasten_screws-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fill_egg_holder-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fill_pen_holder-standard-s0-scene0","l3-o1-r1-mixed42-20261016-fold_clothes-random-s0-scene0","l3-o1-r1-mixed42-20261016-general_pickup-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-hang_mugs-random-s0-scene0","l3-o1-r1-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene0","l3-o1-precision4-20261016-v1-insert_key-standard-s0-scene0","l3-o1-precision4-20261016-v1-insert_tubes-standard-s0-scene0","l3-o1-r1-mixed42-20261016-make_kong-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-make_toast-random-s0-scene0","l3-o1-r1-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-o1-r1-mixed42-20261016-organize_table-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-pack_objects_into_box-random-s0-scene0","l3-o1-r1-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-play_Xylophone-standard-s0-scene0","l3-o1-r1-mixed42-20261016-play_stacking_toy-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-play_tic_tac_toe-standard-s0-scene0","l3-o1-precision4-20261016-v1-plug_in_charger-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_balls_into_vase-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_liquid_into_cup-random-s0-scene0","l3-o1-r1-mixed42-20261016-press_by_number-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-push_T-random-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-put_bottles_into_dustbin-standard-s0-scene0","l3-o1-r1-mixed42-20261016-solve_equation-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-sort_nesting_dolls_by_size-random-s0-scene0","l3-o1-r1-mixed42-20261016-stack_blocks-random-s0-scene0","l3-o1-r1-mixed42-20261016-stack_blocks_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-stack_bowls-random-s0-scene0","l3-o1-r1-mixed42-20261016-store_laptop_and_headphones-random-s0-scene0","l3-o1-r1-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-o1-r1-mixed42-20261016-swap_T-standard-s0-scene0","l3-o1-r1-mixed42-20261016-swap_blocks-standard-s0-scene0","l3-o1-r1-mixed42-20261016-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o1-precision4-20261016-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o1-r1-mixed42-20261016-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.26666666666666666,"success_rate":0.25},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.18125,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5833333333333334,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.5,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.14375,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.335,"selected_run_ids":["l3-o1-r1-mixed42-20261016-align_blocks-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-arrange_largest_number-random-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-build_tower-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-classify_objects-standard-s0-scene0","l3-o1-r1-mixed42-20261016-classify_objects_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-cover_blocks-standard-s0-scene0","l3-o1-precision4-20261016-v1-deposit_coin-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fasten_screws-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fill_egg_holder-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fill_pen_holder-standard-s0-scene0","l3-o1-r1-mixed42-20261016-fold_clothes-random-s0-scene0","l3-o1-r1-mixed42-20261016-general_pickup-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-hang_mugs-random-s0-scene0","l3-o1-r1-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene0","l3-o1-precision4-20261016-v1-insert_key-standard-s0-scene0","l3-o1-precision4-20261016-v1-insert_tubes-standard-s0-scene0","l3-o1-r1-mixed42-20261016-make_kong-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-make_toast-random-s0-scene0","l3-o1-r1-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-o1-r1-mixed42-20261016-organize_table-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-pack_objects_into_box-random-s0-scene0","l3-o1-r1-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-play_Xylophone-standard-s0-scene0","l3-o1-r1-mixed42-20261016-play_stacking_toy-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-play_tic_tac_toe-standard-s0-scene0","l3-o1-precision4-20261016-v1-plug_in_charger-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_balls_into_vase-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_liquid_into_cup-random-s0-scene0","l3-o1-r1-mixed42-20261016-press_by_number-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-push_T-random-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-put_bottles_into_dustbin-standard-s0-scene0","l3-o1-r1-mixed42-20261016-solve_equation-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-sort_nesting_dolls_by_size-random-s0-scene0","l3-o1-r1-mixed42-20261016-stack_blocks-random-s0-scene0","l3-o1-r1-mixed42-20261016-stack_blocks_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-stack_bowls-random-s0-scene0","l3-o1-r1-mixed42-20261016-store_laptop_and_headphones-random-s0-scene0","l3-o1-r1-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-o1-r1-mixed42-20261016-swap_T-standard-s0-scene0","l3-o1-r1-mixed42-20261016-swap_blocks-standard-s0-scene0","l3-o1-r1-mixed42-20261016-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.25,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-classify_objects-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fasten_screws-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-pack_objects_into_box-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-o1-r1-mixed42-20261016-align_blocks-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-arrange_largest_number-random-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-build_tower-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-classify_objects-standard-s0-scene0","l3-o1-r1-mixed42-20261016-classify_objects_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-cover_blocks-standard-s0-scene0","l3-o1-precision4-20261016-v1-deposit_coin-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fasten_screws-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fill_egg_holder-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-fill_pen_holder-standard-s0-scene0","l3-o1-r1-mixed42-20261016-fold_clothes-random-s0-scene0","l3-o1-r1-mixed42-20261016-general_pickup-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-hang_mugs-random-s0-scene0","l3-o1-r1-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene0","l3-o1-precision4-20261016-v1-insert_key-standard-s0-scene0","l3-o1-precision4-20261016-v1-insert_tubes-standard-s0-scene0","l3-o1-r1-mixed42-20261016-make_kong-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-make_toast-random-s0-scene0","l3-o1-r1-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene0","l3-o1-r1-mixed42-20261016-organize_table-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-pack_objects_into_box-random-s0-scene0","l3-o1-r1-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-play_Xylophone-standard-s0-scene0","l3-o1-r1-mixed42-20261016-play_stacking_toy-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-play_tic_tac_toe-standard-s0-scene0","l3-o1-precision4-20261016-v1-plug_in_charger-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_balls_into_vase-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-pour_liquid_into_cup-random-s0-scene0","l3-o1-r1-mixed42-20261016-press_by_number-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-push_T-random-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-put_bottles_into_dustbin-standard-s0-scene0","l3-o1-r1-mixed42-20261016-solve_equation-standard-s0-scene0","l3-o1-r1-mixed42-retry01-20261017-sort_nesting_dolls_by_size-random-s0-scene0","l3-o1-r1-mixed42-20261016-stack_blocks-random-s0-scene0","l3-o1-r1-mixed42-20261016-stack_blocks_by_language-standard-s0-scene0","l3-o1-r1-mixed42-20261016-stack_bowls-random-s0-scene0","l3-o1-r1-mixed42-20261016-store_laptop_and_headphones-random-s0-scene0","l3-o1-r1-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene0","l3-o1-r1-mixed42-20261016-swap_T-standard-s0-scene0","l3-o1-r1-mixed42-20261016-swap_blocks-standard-s0-scene0","l3-o1-r1-mixed42-20261016-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o1-precision4-20261016-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o1-precision4-20261016-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-retry01-20261017-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o1-r1-mixed42-20261016-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o1-r1-mixed42-20261016-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"0b2f853b9a3a3aa4feded62643e6b1b3a1261fdf6dbd0ed8dac8052bd5f797cd","name":"persistent-cap20-o1 · medium · R1","selection_id":"l3-o1-r1-mixed42-20261016"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-o2-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o2-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o2-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o2-precision4-20261017-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o2-precision4-20261017-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["l3-o2-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o2-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o2-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o2-precision4-20261017-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-o2-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o2-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o2-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o2-precision4-20261017-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o2-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o2-precision4-20261017-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"e7f59eacb0acac77038d9d4eab8feaa00896bb8f1cfd6dd2a868d91f402c1b76","name":"l3-o2-precision4-20261017-v1","selection_id":"l3-o2-precision4-20261017-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.5229166666666667,"success_rate":0.4791666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.315625,"success_rate":0.15625},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.55625,"success_rate":0.5416666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.51875,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.20625000000000002,"success_rate":0.09375}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.4239583333333334,"selected_run_ids":["l3-o23-depthpro-precision4-20261019-a3-align_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-align_blocks-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a4-arrange_largest_number-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-arrange_largest_number-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a2-build_tower-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-classify_objects-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-classify_objects_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects_by_language-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-cover_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-cover_blocks-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a2-deposit_coin-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-fasten_screws-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-fasten_screws-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a4-fill_egg_holder-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-fill_pen_holder-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-fold_clothes-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-fold_clothes-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-general_pickup-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-general_pickup-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a4-hang_mugs-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-imitate_sorting_sequence-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-imitate_sorting_sequence-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-v1-insert_key-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a2-insert_tubes-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-make_kong-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-make_toast-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-match_and_pick_from_conveyor-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-organize_table-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-pack_objects_into_box-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pack_objects_into_box-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pick_from_conveyor_by_image-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a2-play_Xylophone-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-play_Xylophone-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-play_stacking_toy-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-play_tic_tac_toe-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-plug_in_charger-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-plug_in_charger-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-pour_balls_into_vase-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pour_balls_into_vase-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-pour_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-pour_liquid_into_cup-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-press_by_number-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-press_by_number-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a4-push_T-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-push_T-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a4-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-solve_equation-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-solve_equation-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a4-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-sort_nesting_dolls_by_size-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a4-stack_blocks-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-stack_blocks_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-stack_blocks_by_language-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-stack_bowls-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-stack_bowls-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a4-store_laptop_and_headphones-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-store_tools_in_toolbox-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-swap_T-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-swap_T-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene3","l3-o23-depthpro-precision4-20261019-a3-swap_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.35416666666666663,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-align_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-align_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-arrange_largest_number-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-arrange_largest_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-classify_objects-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-classify_objects_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects_by_language-standard-s0-scene3"],"score":0.15000000000000002,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-cover_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-cover_blocks-standard-s0-scene3"],"score":0.7625,"success_rate":0.75,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fasten_screws-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-fasten_screws-standard-s0-scene3"],"score":0.8,"success_rate":0.75,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-fold_clothes-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-fold_clothes-standard-s0-scene1"],"score":0.8,"success_rate":0.75,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-general_pickup-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-imitate_sorting_sequence-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-imitate_sorting_sequence-standard-s0-scene3"],"score":0.575,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-make_toast-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-pack_objects_into_box-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pack_objects_into_box-standard-s0-scene1"],"score":0.275,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-play_Xylophone-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-play_Xylophone-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-plug_in_charger-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pour_balls_into_vase-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-press_by_number-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-push_T-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-push_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.475,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-solve_equation-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-solve_equation-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-stack_blocks_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-stack_blocks_by_language-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-stack_bowls-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-random-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-stack_bowls-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-swap_T-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-p50supp1-swap_T-standard-s0-scene2","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.6416666666666667,"success_rate":0.5833333333333334},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2875,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6749999999999999,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.55,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.23125,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.4770833333333333,"selected_run_ids":["l3-o23-depthpro-precision4-20261019-a3-align_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-arrange_largest_number-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a2-build_tower-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-classify_objects-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-classify_objects_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-cover_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a2-deposit_coin-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-fasten_screws-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-fill_egg_holder-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-fill_pen_holder-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-fold_clothes-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-general_pickup-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-hang_mugs-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-imitate_sorting_sequence-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-insert_key-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a2-insert_tubes-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-make_kong-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-make_toast-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-organize_table-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-pack_objects_into_box-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a2-play_Xylophone-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-play_stacking_toy-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-play_tic_tac_toe-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-plug_in_charger-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-pour_balls_into_vase-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-pour_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-pour_liquid_into_cup-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-press_by_number-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-push_T-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-solve_equation-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-stack_blocks-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-stack_blocks_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-stack_bowls-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-store_laptop_and_headphones-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-store_tools_in_toolbox-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-swap_T-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-swap_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.4,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-cover_blocks-standard-s0-scene0"],"score":0.05,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fasten_screws-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-make_toast-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-pack_objects_into_box-random-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-sort_nesting_dolls_by_size-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-swap_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.6416666666666667,"success_rate":0.5833333333333334},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.334375,"success_rate":0.1875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5875,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.53125,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.18125,"success_rate":0.0625}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.4552083333333333,"selected_run_ids":["l3-o23-depthpro-precision4-20261019-a3-align_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a4-arrange_largest_number-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a2-build_tower-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-classify_objects-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-classify_objects_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-cover_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a2-deposit_coin-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-fasten_screws-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a4-fill_egg_holder-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-fill_pen_holder-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-fold_clothes-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-general_pickup-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a4-hang_mugs-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-imitate_sorting_sequence-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-v1-insert_key-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a2-insert_tubes-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-make_kong-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-make_toast-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-organize_table-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-pack_objects_into_box-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a2-play_Xylophone-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-play_stacking_toy-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-play_tic_tac_toe-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-plug_in_charger-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-pour_balls_into_vase-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-pour_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-pour_liquid_into_cup-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-press_by_number-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a4-push_T-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-solve_equation-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a4-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-stack_blocks-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-stack_blocks_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-stack_bowls-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-store_laptop_and_headphones-random-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-store_tools_in_toolbox-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a3-swap_T-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene1","l3-o23-depthpro-precision4-20261019-a3-swap_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-a4-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.38333333333333336,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-align_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-align_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-arrange_largest_number-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-classify_objects-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-classify_objects-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-classify_objects_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-classify_objects_by_language-standard-s0-scene1"],"score":0.25,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-cover_blocks-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-cover_blocks-standard-s0-scene1"],"score":0.525,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fasten_screws-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fasten_screws-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-fold_clothes-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-fold_clothes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-general_pickup-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-imitate_sorting_sequence-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-imitate_sorting_sequence-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-make_toast-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-pack_objects_into_box-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pack_objects_into_box-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a2-play_Xylophone-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-plug_in_charger-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pour_balls_into_vase-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-press_by_number-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-press_by_number-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-push_T-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-push_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.625,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-solve_equation-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-stack_blocks_by_language-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_blocks_by_language-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-stack_bowls-random-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-swap_T-standard-s0-scene0","l3-o23-depthpro-precision4-20261019-v1-p50supp1-retry1-swap_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a3-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-depthpro-precision4-20261019-a4-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"06cfd12b11cbe13b5b6b9b3001f9a0056f93f14f6bdd4dfcc7ef4f36d2afa331","name":"persistent-cap20-o23-depthpro","selection_id":"l3-o23-depthpro-precision4-20261019-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4239583333333334,"success_rate":0.3958333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2921875,"success_rate":0.0625},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.7291666666666666,"success_rate":0.7083333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.56875,"success_rate":0.5625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.2875,"success_rate":0.1875}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.4603125,"selected_run_ids":["l3-o23-full-ik42-medium-r1-20261017-align_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-align_blocks-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-arrange_largest_number-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-random-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-arrange_largest_number-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-build_tower-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-classify_objects-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-classify_objects-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-classify_objects_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-classify_objects_by_language-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-cover_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-cover_blocks-standard-s0-scene3","l3-o23-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fasten_screws-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene2","l3-o23-graphics51-20261023T195942-10dd112b-fasten_screws-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-fill_egg_holder-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fill_pen_holder-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fold_clothes-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fold_clothes-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fold_clothes-random-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-fold_clothes-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-general_pickup-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-general_pickup-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-hang_mugs-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-imitate_sorting_sequence-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-imitate_sorting_sequence-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-imitate_sorting_sequence-standard-s0-scene2","l3-o23-transport-restart-20261023T163714-ff793d1e-imitate_sorting_sequence-standard-s0-scene3","l3-o23-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o23-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-make_kong-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-make_toast-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-match_and_pick_from_conveyor-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-organize_table-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pack_objects_into_box-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-random-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-pack_objects_into_box-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-pick_from_conveyor_by_image-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-play_Xylophone-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-play_Xylophone-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-play_stacking_toy-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-play_tic_tac_toe-standard-s0-scene0","l3-o23-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-plug_in_charger-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-pour_balls_into_vase-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene2","l3-o23-fresh36-independent-20261023T142520-286e4995-pour_balls_into_vase-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-pour_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pour_liquid_into_cup-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-press_by_number-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene2","l3-o23-fresh36-independent-20261023T142520-286e4995-press_by_number-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-push_T-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-push_T-standard-s0-scene0","l3-o23-fresh36-20261023-run3-d541ea2b-push_T-random-s0-scene1","l3-o23-fresh36-independent-20261023T142520-286e4995-push_T-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-put_bottles_into_dustbin-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-put_bottles_into_dustbin-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-put_bottles_into_dustbin-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-solve_equation-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-solve_equation-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-solve_equation-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-solve_equation-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o23-fresh36-20261023-run3-d541ea2b-sort_nesting_dolls_by_size-random-s0-scene1","l3-o23-native-wait-20261023T151947-292d3cc8-sort_nesting_dolls_by_size-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-stack_blocks-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-stack_blocks_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-stack_blocks_by_language-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-stack_blocks_by_language-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-stack_blocks_by_language-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-stack_bowls-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-stack_bowls-standard-s0-scene0","l3-o23-fresh36-20261023-run3-d541ea2b-stack_bowls-random-s0-scene1","l3-o23-fresh36-independent-20261023T142520-286e4995-stack_bowls-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-store_laptop_and_headphones-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-store_tools_in_toolbox-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-swap_T-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-swap_T-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-swap_T-standard-s0-scene2","l3-o23-dynamic-gpu-20261023T160639-d299cf75-swap_T-standard-s0-scene3","l3-o23-full-ik42-medium-r1-20261017-swap_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.38333333333333336,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-align_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-align_blocks-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-arrange_largest_number-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-random-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-arrange_largest_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-classify_objects-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-classify_objects-standard-s0-scene3"],"score":0.4875,"success_rate":0.25,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-classify_objects_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-classify_objects_by_language-standard-s0-scene3"],"score":0.3,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-cover_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-cover_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fasten_screws-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene2","l3-o23-graphics51-20261023T195942-10dd112b-fasten_screws-standard-s0-scene3"],"score":0.15000000000000002,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fold_clothes-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fold_clothes-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fold_clothes-random-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-fold_clothes-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-general_pickup-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-imitate_sorting_sequence-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-imitate_sorting_sequence-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-imitate_sorting_sequence-standard-s0-scene2","l3-o23-transport-restart-20261023T163714-ff793d1e-imitate_sorting_sequence-standard-s0-scene3"],"score":0.875,"success_rate":0.75,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pack_objects_into_box-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-random-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-pack_objects_into_box-standard-s0-scene1"],"score":0.3,"success_rate":0.25,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_Xylophone-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-play_Xylophone-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o23-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-plug_in_charger-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_balls_into_vase-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene2","l3-o23-fresh36-independent-20261023T142520-286e4995-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-press_by_number-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene1","l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene2","l3-o23-fresh36-independent-20261023T142520-286e4995-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-push_T-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-push_T-standard-s0-scene0","l3-o23-fresh36-20261023-run3-d541ea2b-push_T-random-s0-scene1","l3-o23-fresh36-independent-20261023T142520-286e4995-push_T-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-put_bottles_into_dustbin-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-put_bottles_into_dustbin-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-solve_equation-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-solve_equation-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-solve_equation-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-solve_equation-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o23-fresh36-20261023-run3-d541ea2b-sort_nesting_dolls_by_size-random-s0-scene1","l3-o23-native-wait-20261023T151947-292d3cc8-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_blocks_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-stack_blocks_by_language-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-stack_blocks_by_language-standard-s0-scene2","l3-o23-fresh36-20261023-run3-d541ea2b-stack_blocks_by_language-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_bowls-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-stack_bowls-standard-s0-scene0","l3-o23-fresh36-20261023-run3-d541ea2b-stack_bowls-random-s0-scene1","l3-o23-fresh36-independent-20261023T142520-286e4995-stack_bowls-standard-s0-scene1"],"score":0.5375,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-swap_T-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-swap_T-standard-s0-scene1","l3-o23-fresh36-20261023-run3-d541ea2b-swap_T-standard-s0-scene2","l3-o23-dynamic-gpu-20261023T160639-d299cf75-swap_T-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.5958333333333333,"success_rate":0.5833333333333334},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2625,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.75,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.75,"success_rate":0.75},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.23125,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.5179166666666667,"selected_run_ids":["l3-o23-full-ik42-medium-r1-20261017-align_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-arrange_largest_number-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-build_tower-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-classify_objects-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-classify_objects_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-cover_blocks-standard-s0-scene0","l3-o23-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fasten_screws-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fill_egg_holder-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fill_pen_holder-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fold_clothes-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-general_pickup-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-hang_mugs-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-imitate_sorting_sequence-standard-s0-scene0","l3-o23-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o23-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-make_kong-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-make_toast-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-organize_table-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pack_objects_into_box-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-play_Xylophone-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-play_stacking_toy-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-play_tic_tac_toe-standard-s0-scene0","l3-o23-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pour_balls_into_vase-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pour_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pour_liquid_into_cup-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-press_by_number-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-push_T-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-solve_equation-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-stack_blocks-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-stack_blocks_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-stack_bowls-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-store_laptop_and_headphones-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-store_tools_in_toolbox-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-swap_T-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-swap_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.425,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-imitate_sorting_sequence-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pack_objects_into_box-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pick_from_conveyor_by_image-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-sort_nesting_dolls_by_size-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-swap_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.525,"success_rate":0.5},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.3,"success_rate":0.0625},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.7916666666666666,"success_rate":0.75},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.63125,"success_rate":0.625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.29375,"success_rate":0.1875}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.5083333333333333,"selected_run_ids":["l3-o23-full-ik42-medium-r1-20261017-align_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-arrange_largest_number-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-build_tower-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-classify_objects-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-classify_objects_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-cover_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene1","l3-o23-precision4-20261017-v1-deposit_coin-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fasten_screws-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-fill_egg_holder-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fill_pen_holder-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-fold_clothes-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fold_clothes-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-general_pickup-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-hang_mugs-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-imitate_sorting_sequence-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-imitate_sorting_sequence-standard-s0-scene1","l3-o23-precision4-20261017-v1-insert_key-standard-s0-scene0","l3-o23-precision4-20261017-v1-insert_tubes-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-make_kong-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-make_toast-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-organize_table-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pack_objects_into_box-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-play_Xylophone-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-play_stacking_toy-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-play_tic_tac_toe-standard-s0-scene0","l3-o23-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-pour_balls_into_vase-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-pour_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-pour_liquid_into_cup-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-press_by_number-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-push_T-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-push_T-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-put_bottles_into_dustbin-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-solve_equation-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-solve_equation-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-stack_blocks-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-stack_blocks_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-stack_blocks_by_language-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-stack_bowls-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-stack_bowls-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-store_laptop_and_headphones-random-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-store_tools_in_toolbox-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-swap_T-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-swap_T-standard-s0-scene1","l3-o23-full-ik42-medium-r1-20261017-swap_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-r1-20261017-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.425,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-align_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-align_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-arrange_largest_number-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-classify_objects-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-classify_objects-standard-s0-scene1"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-classify_objects_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-classify_objects_by_language-standard-s0-scene1"],"score":0.55,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-cover_blocks-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fasten_screws-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fasten_screws-standard-s0-scene1"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-fold_clothes-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-fold_clothes-standard-s0-scene0"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-general_pickup-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-imitate_sorting_sequence-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-imitate_sorting_sequence-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23-precision4-20261017-v1-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pack_objects_into_box-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pack_objects_into_box-standard-s0-scene0"],"score":0.55,"success_rate":0.5,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_Xylophone-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o23-precision4-20261017-v1-plug_in_charger-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-plug_in_charger-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_balls_into_vase-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-press_by_number-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-push_T-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-push_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-put_bottles_into_dustbin-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-solve_equation-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_blocks_by_language-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-stack_blocks_by_language-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-stack_bowls-random-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-swap_T-standard-s0-scene0","l3-o23-full-ik42-medium-devset-20261021-swap_T-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23-full-ik42-medium-r1-20261017-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"c67720968234ad2206ff31a7d34999c9435e0afeba70bc411a75aadc37cc83e6","name":"persistent-cap20-o23","selection_id":"l3-o23-full-ik42-medium-r1-20261017"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-o23456-clear-full42-20261023-v1-align_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-arrange_largest_number-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-build_tower-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-classify_objects-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-classify_objects_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-cover_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-deposit_coin-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fasten_screws-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fill_egg_holder-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fill_pen_holder-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fold_clothes-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-general_pickup-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-hang_mugs-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-imitate_sorting_sequence-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-insert_key-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-insert_tubes-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-make_kong-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-make_toast-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-organize_table-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pack_objects_into_box-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-sim60-recovery1-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_Xylophone-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_stacking_toy-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_tic_tac_toe-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-plug_in_charger-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pour_balls_into_vase-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pour_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sim51-recovery1-pour_liquid_into_cup-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-press_by_number-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-push_T-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-solve_equation-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_blocks-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_blocks_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_bowls-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-store_laptop_and_headphones-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-store_tools_in_toolbox-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-swap_T-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-swap_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-sim60-recovery1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-sim51-recovery1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["l3-o23456-clear-full42-20261023-v1-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.30833333333333335,"success_rate":0.25},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.14375,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5499999999999999,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.55,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.20625,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.3516666666666667,"selected_run_ids":["l3-o23456-clear-full42-20261023-v1-align_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-arrange_largest_number-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-build_tower-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-classify_objects-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-classify_objects_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-cover_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-deposit_coin-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fasten_screws-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fill_egg_holder-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fill_pen_holder-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fold_clothes-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-general_pickup-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-hang_mugs-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-imitate_sorting_sequence-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-insert_key-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-insert_tubes-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-make_kong-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-make_toast-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-organize_table-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pack_objects_into_box-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-sim60-recovery1-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_Xylophone-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_stacking_toy-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_tic_tac_toe-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-plug_in_charger-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pour_balls_into_vase-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pour_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sim51-recovery1-pour_liquid_into_cup-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-press_by_number-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-push_T-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-solve_equation-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_blocks-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_blocks_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_bowls-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-store_laptop_and_headphones-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-store_tools_in_toolbox-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-swap_T-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-swap_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.275,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-arrange_largest_number-random-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-imitate_sorting_sequence-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-pack_objects_into_box-random-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-sim60-recovery1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-sim51-recovery1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_bowls-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-o23456-clear-full42-20261023-v1-align_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-arrange_largest_number-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-build_tower-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-classify_objects-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-classify_objects_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-cover_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-deposit_coin-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fasten_screws-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fill_egg_holder-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fill_pen_holder-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-fold_clothes-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-general_pickup-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-hang_mugs-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-imitate_sorting_sequence-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-insert_key-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-insert_tubes-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-make_kong-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-make_toast-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-organize_table-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pack_objects_into_box-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-sim60-recovery1-pick_from_conveyor_by_image-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_Xylophone-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_stacking_toy-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-play_tic_tac_toe-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-plug_in_charger-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pour_balls_into_vase-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-pour_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sim51-recovery1-pour_liquid_into_cup-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-press_by_number-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-push_T-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-solve_equation-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_blocks-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_blocks_by_language-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-stack_bowls-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-store_laptop_and_headphones-random-s0-scene0","l3-o23456-clear-full42-20261023-v1-store_tools_in_toolbox-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-swap_T-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-swap_blocks-standard-s0-scene0","l3-o23456-clear-full42-20261023-v1-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-sim60-recovery1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-sim51-recovery1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["l3-o23456-clear-full42-20261023-v1-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-clear-full42-20261023-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"5e605940d01cf6fb166d14b9f4d57284857862eca2236ebd86b017f986cbc071","name":"O23456-clear · 首轮42项","selection_id":"l3-o23456-clear-full42-20261023-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":1,"expected_tasks":8,"score":null,"success_rate":null}},"completed":1,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-o23456-generation-precision1-20261021-v1-initretry01-insert_key-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-generation-precision1-20261021-v1-initretry01-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":1,"expected_tasks":8,"score":null,"success_rate":null}},"completed":1,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["l3-o23456-generation-precision1-20261021-v1-initretry01-insert_key-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-generation-precision1-20261021-v1-initretry01-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":1,"expected_tasks":8,"score":null,"success_rate":null}},"completed":1,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-o23456-generation-precision1-20261021-v1-initretry01-insert_key-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-generation-precision1-20261021-v1-initretry01-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"0cdde47219da48d5a2af5a18a610949135d388f3f9f601fb82207f79ff957f3c","name":"l3-o23456-generation-precision1-20261021-v1","selection_id":"l3-o23456-generation-precision1-20261021-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":19,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-o23456-pure-generalization12-20261020-v1-arrange_largest_number-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-build_tower-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-deposit_coin-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-fasten_screws-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-fold_clothes-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-hang_mugs-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-insert_key-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-insert_tubes-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-make_toast-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-pack_objects_into_box-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-play_Xylophone-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-plug_in_charger-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-pour_balls_into_vase-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-pour_liquid_into_cup-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-push_T-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-stack_blocks-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-store_laptop_and_headphones-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o23456-pure-precision8-20261020-v1-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o23456-pure-precision8-20261020-v1-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o23456-pure-precision8-20261020-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o23456-pure-precision8-20261020-v1-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":11,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.05625,"success_rate":0.0}},"completed":19,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"}],"plan_id":"first_round","score":null,"selected_run_ids":["l3-o23456-pure-generalization12-20261020-v1-arrange_largest_number-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-build_tower-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-deposit_coin-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-fasten_screws-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-fold_clothes-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-hang_mugs-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-insert_key-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-insert_tubes-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-make_toast-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-pack_objects_into_box-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-play_Xylophone-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-plug_in_charger-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-pour_balls_into_vase-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-pour_liquid_into_cup-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-push_T-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-stack_blocks-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-store_laptop_and_headphones-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-pack_objects_into_box-random-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":19,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-o23456-pure-generalization12-20261020-v1-arrange_largest_number-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-build_tower-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-deposit_coin-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-fasten_screws-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-fold_clothes-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-hang_mugs-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-insert_key-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-insert_tubes-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-make_toast-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-pack_objects_into_box-random-s0-scene0","l3-o23456-pure-precision8-20261020-v1-play_Xylophone-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-plug_in_charger-standard-s0-scene0","l3-o23456-pure-precision8-20261020-v1-pour_balls_into_vase-standard-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-pour_liquid_into_cup-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-push_T-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-stack_blocks-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-store_laptop_and_headphones-random-s0-scene0","l3-o23456-pure-generalization12-20261020-v1-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o23456-pure-precision8-20261020-v1-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o23456-pure-precision8-20261020-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o23456-pure-precision8-20261020-v1-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o23456-pure-precision8-20261020-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o23456-pure-precision8-20261020-v1-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o23456-pure-generalization12-20261020-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"6d1b1f0d10060c7299848b6929284a648d93c02a1bc2955d3838d2b675d3e4fa","name":"persistent-cap20-o23456-pure","selection_id":"l3-o23456-pure-20261020"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-o4-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o4-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o4-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o4-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o4-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["l3-o4-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o4-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o4-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o4-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-o4-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o4-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o4-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o4-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o4-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o4-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"53f2c14091824b5686890ec91ff23b8a5f1eab741789413c19b66d8758a460c3","name":"l3-o4-precision4-20261018-v1","selection_id":"l3-o4-precision4-20261018-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["l3-o45-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o45-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o45-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o45-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["l3-o45-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["l3-o45-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o45-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o45-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o45-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null}},"completed":4,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["l3-o45-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o45-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o45-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o45-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o45-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["l3-o45-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"37554043e6e2baf373de820f2a03adef34af89f64e7746ab71cbe0dba7d8eb7c","name":"l3-o45-precision4-20261018-v1","selection_id":"l3-o45-precision4-20261018-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.37395833333333334,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2171875,"success_rate":0.09375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.7208333333333333,"success_rate":0.7083333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.43125,"success_rate":0.40625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.09375,"success_rate":0.0}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.3673958333333333,"selected_run_ids":["l3-o456-clear-olm22-medium-r1-20261019-align_blocks-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene3","l3-o456-clear-generalization12-20261019-v1-arrange_largest_number-random-s0-scene0","l3-o456-remainder12-20261026T213800-arrange_largest_number-standard-s0-scene0","l3-o456-remainder12-20261026T213800-arrange_largest_number-random-s0-scene1","l3-o456-refill12-20261027T030000-arrange_largest_number-standard-s0-scene1","l3-o456-clear-precision8-completion-20261019-v1-build_tower-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-classify_objects-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene2","l3-o456-o456-repaired-20261024T000632-e66c6663-classify_objects-standard-s0-scene3","l3-o456-clear-olm22-medium-r1-20261019-classify_objects_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene2","l3-o456-o456-repaired-20261024T000632-e66c6663-classify_objects_by_language-standard-s0-scene3","l3-o456-clear-olm22-medium-r1-20261019-cover_blocks-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene3","l3-o456-clear-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o456-clear-precision8-completion-20261019-v1-fasten_screws-standard-s0-scene0","l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene1","l3-o456-complement30-20261025-fasten_screws-standard-s0-scene2","l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene3","l3-o456-clear-olm22-medium-r1-20261019-fill_egg_holder-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-fill_pen_holder-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-fold_clothes-random-s0-scene0","l3-o456-complement30-20261025-fold_clothes-standard-s0-scene0","l3-o456-remainder12-20261026T213800-fold_clothes-random-s0-scene1","l3-o456-refill12-20261027T030000-fold_clothes-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-general_pickup-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene3","l3-o456-clear-generalization12-20261019-v1-hang_mugs-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-imitate_sorting_sequence-standard-s0-scene0","l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene1","l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene2","l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene3","l3-o456-clear-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o456-clear-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-make_kong-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-make_toast-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-match_and_pick_from_conveyor-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene3","l3-o456-clear-olm22-medium-r1-20261019-organize_table-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-pack_objects_into_box-random-s0-scene0","l3-o456-remainder12-20261026T213800-pack_objects_into_box-standard-s0-scene0","l3-o456-remainder12-20261026T213800-pack_objects_into_box-random-s0-scene1","l3-o456-refill12-20261027T030000-pack_objects_into_box-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-pick_from_conveyor_by_image-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene3","l3-o456-clear-precision8-completion-20261019-v1-play_Xylophone-standard-s0-scene0","l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene1","l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene2","l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene3","l3-o456-clear-olm22-medium-r1-20261019-play_stacking_toy-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-play_tic_tac_toe-standard-s0-scene0","l3-o456-clear-precision4-20261018-v1-plug_in_charger-standard-s0-scene0","l3-o456-complement30-20261025-plug_in_charger-standard-s0-scene1","l3-o456-remainder12-20261026T213800-plug_in_charger-standard-s0-scene2","l3-o456-remainder12-20261026T213800-plug_in_charger-standard-s0-scene3","l3-o456-clear-precision8-completion-20261019-v1-pour_balls_into_vase-standard-s0-scene0","l3-o456-complement30-20261025-pour_balls_into_vase-standard-s0-scene1","l3-o456-remainder12-20261026T213800-pour_balls_into_vase-standard-s0-scene2","l3-o456-refill12-20261027T030000-pour_balls_into_vase-standard-s0-scene3","l3-o456-clear-olm22-medium-r1-20261019-pour_by_language-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-press_by_number-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene3","l3-o456-clear-generalization12-20261019-v1-push_T-random-s0-scene0","l3-o456-remainder12-20261026T213800-push_T-standard-s0-scene0","l3-o456-remainder12-20261026T213800-push_T-random-s0-scene1","l3-o456-refill12-20261027T030000-push_T-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-put_bottles_into_dustbin-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene3","l3-o456-clear-olm22-medium-r1-20261019-solve_equation-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene3","l3-o456-clear-generalization12-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o456-complement30-20261025-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o456-remainder12-20261026T213800-sort_nesting_dolls_by_size-random-s0-scene1","l3-o456-refill12-20261027T030000-sort_nesting_dolls_by_size-standard-s0-scene1","l3-o456-clear-generalization12-20261019-v1-stack_blocks-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-stack_blocks_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene3","l3-o456-clear-generalization12-20261019-v1-stack_bowls-random-s0-scene0","l3-o456-remainder12-20261026T213800-stack_bowls-standard-s0-scene0","l3-o456-remainder12-20261026T213800-stack_bowls-random-s0-scene1","l3-o456-refill12-20261027T030000-stack_bowls-standard-s0-scene1","l3-o456-clear-generalization12-20261019-v1-store_laptop_and_headphones-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-store_tools_in_toolbox-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-swap_T-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene3","l3-o456-clear-olm22-medium-r1-20261019-swap_blocks-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.30833333333333335,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-align_blocks-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o456-clear-generalization12-20261019-v1-arrange_largest_number-random-s0-scene0","l3-o456-remainder12-20261026T213800-arrange_largest_number-standard-s0-scene0","l3-o456-remainder12-20261026T213800-arrange_largest_number-random-s0-scene1","l3-o456-refill12-20261027T030000-arrange_largest_number-standard-s0-scene1"],"score":0.85,"success_rate":0.75,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-classify_objects-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene2","l3-o456-o456-repaired-20261024T000632-e66c6663-classify_objects-standard-s0-scene3"],"score":0.6375,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-classify_objects_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene2","l3-o456-o456-repaired-20261024T000632-e66c6663-classify_objects_by_language-standard-s0-scene3"],"score":0.15000000000000002,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-cover_blocks-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-fasten_screws-standard-s0-scene0","l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene1","l3-o456-complement30-20261025-fasten_screws-standard-s0-scene2","l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene3"],"score":0.1,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o456-clear-generalization12-20261019-v1-fold_clothes-random-s0-scene0","l3-o456-complement30-20261025-fold_clothes-standard-s0-scene0","l3-o456-remainder12-20261026T213800-fold_clothes-random-s0-scene1","l3-o456-refill12-20261027T030000-fold_clothes-standard-s0-scene1"],"score":0.8,"success_rate":0.75,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-general_pickup-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-imitate_sorting_sequence-standard-s0-scene0","l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene1","l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene2","l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene3"],"score":0.825,"success_rate":0.75,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-match_and_pick_from_conveyor-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o456-clear-generalization12-20261019-v1-pack_objects_into_box-random-s0-scene0","l3-o456-remainder12-20261026T213800-pack_objects_into_box-standard-s0-scene0","l3-o456-remainder12-20261026T213800-pack_objects_into_box-random-s0-scene1","l3-o456-refill12-20261027T030000-pack_objects_into_box-standard-s0-scene1"],"score":0.3375,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-pick_from_conveyor_by_image-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-play_Xylophone-standard-s0-scene0","l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene1","l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene2","l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o456-clear-precision4-20261018-v1-plug_in_charger-standard-s0-scene0","l3-o456-complement30-20261025-plug_in_charger-standard-s0-scene1","l3-o456-remainder12-20261026T213800-plug_in_charger-standard-s0-scene2","l3-o456-remainder12-20261026T213800-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-pour_balls_into_vase-standard-s0-scene0","l3-o456-complement30-20261025-pour_balls_into_vase-standard-s0-scene1","l3-o456-remainder12-20261026T213800-pour_balls_into_vase-standard-s0-scene2","l3-o456-refill12-20261027T030000-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-press_by_number-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o456-clear-generalization12-20261019-v1-push_T-random-s0-scene0","l3-o456-remainder12-20261026T213800-push_T-standard-s0-scene0","l3-o456-remainder12-20261026T213800-push_T-random-s0-scene1","l3-o456-refill12-20261027T030000-push_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-put_bottles_into_dustbin-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-solve_equation-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o456-clear-generalization12-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o456-complement30-20261025-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o456-remainder12-20261026T213800-sort_nesting_dolls_by_size-random-s0-scene1","l3-o456-refill12-20261027T030000-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-stack_blocks_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene3"],"score":0.8,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-o456-clear-generalization12-20261019-v1-stack_bowls-random-s0-scene0","l3-o456-remainder12-20261026T213800-stack_bowls-standard-s0-scene0","l3-o456-remainder12-20261026T213800-stack_bowls-random-s0-scene1","l3-o456-refill12-20261027T030000-stack_bowls-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-swap_T-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene1","l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene2","l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.28750000000000003,"success_rate":0.25},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.24375,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.425,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.10625000000000001,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.3458333333333333,"selected_run_ids":["l3-o456-clear-olm22-medium-r1-20261019-align_blocks-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-arrange_largest_number-random-s0-scene0","l3-o456-clear-precision8-completion-20261019-v1-build_tower-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-classify_objects-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-classify_objects_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-cover_blocks-standard-s0-scene0","l3-o456-clear-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o456-clear-precision8-completion-20261019-v1-fasten_screws-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-fill_egg_holder-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-fill_pen_holder-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-fold_clothes-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-general_pickup-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-hang_mugs-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-imitate_sorting_sequence-standard-s0-scene0","l3-o456-clear-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o456-clear-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-make_kong-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-make_toast-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-match_and_pick_from_conveyor-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-organize_table-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-pack_objects_into_box-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-pick_from_conveyor_by_image-standard-s0-scene0","l3-o456-clear-precision8-completion-20261019-v1-play_Xylophone-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-play_stacking_toy-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-play_tic_tac_toe-standard-s0-scene0","l3-o456-clear-precision4-20261018-v1-plug_in_charger-standard-s0-scene0","l3-o456-clear-precision8-completion-20261019-v1-pour_balls_into_vase-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-pour_by_language-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-press_by_number-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-push_T-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-put_bottles_into_dustbin-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-solve_equation-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o456-clear-generalization12-20261019-v1-stack_blocks-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-stack_blocks_by_language-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-stack_bowls-random-s0-scene0","l3-o456-clear-generalization12-20261019-v1-store_laptop_and_headphones-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-store_tools_in_toolbox-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-swap_T-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-swap_blocks-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2833333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-pack_objects_into_box-random-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.35625,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.28125,"success_rate":0.1875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.75,"success_rate":0.75},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.41875,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.10625000000000001,"success_rate":0.0}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.3825,"selected_run_ids":["l3-o456-clear-olm22-medium-r1-20261019-align_blocks-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene1","l3-o456-clear-generalization12-20261019-v1-arrange_largest_number-random-s0-scene0","l3-o456-remainder12-20261026T213800-arrange_largest_number-standard-s0-scene0","l3-o456-clear-precision8-completion-20261019-v1-build_tower-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-classify_objects-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-classify_objects_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-cover_blocks-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene1","l3-o456-clear-precision4-20261018-v1-deposit_coin-standard-s0-scene0","l3-o456-clear-precision8-completion-20261019-v1-fasten_screws-standard-s0-scene0","l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-fill_egg_holder-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-fill_pen_holder-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-fold_clothes-random-s0-scene0","l3-o456-complement30-20261025-fold_clothes-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-general_pickup-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene1","l3-o456-clear-generalization12-20261019-v1-hang_mugs-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-imitate_sorting_sequence-standard-s0-scene0","l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene1","l3-o456-clear-precision4-20261018-v1-insert_key-standard-s0-scene0","l3-o456-clear-precision4-20261018-v1-insert_tubes-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-make_kong-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-make_toast-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-match_and_pick_from_conveyor-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-organize_table-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-pack_objects_into_box-random-s0-scene0","l3-o456-remainder12-20261026T213800-pack_objects_into_box-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-pick_from_conveyor_by_image-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene1","l3-o456-clear-precision8-completion-20261019-v1-play_Xylophone-standard-s0-scene0","l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-play_stacking_toy-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-play_tic_tac_toe-standard-s0-scene0","l3-o456-clear-precision4-20261018-v1-plug_in_charger-standard-s0-scene0","l3-o456-complement30-20261025-plug_in_charger-standard-s0-scene1","l3-o456-clear-precision8-completion-20261019-v1-pour_balls_into_vase-standard-s0-scene0","l3-o456-complement30-20261025-pour_balls_into_vase-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-pour_by_language-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-press_by_number-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene1","l3-o456-clear-generalization12-20261019-v1-push_T-random-s0-scene0","l3-o456-remainder12-20261026T213800-push_T-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-put_bottles_into_dustbin-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-solve_equation-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene1","l3-o456-clear-generalization12-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o456-complement30-20261025-sort_nesting_dolls_by_size-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-stack_blocks-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-stack_blocks_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene1","l3-o456-clear-generalization12-20261019-v1-stack_bowls-random-s0-scene0","l3-o456-remainder12-20261026T213800-stack_bowls-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-store_laptop_and_headphones-random-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-store_tools_in_toolbox-standard-s0-scene0","l3-o456-clear-olm22-medium-r1-20261019-swap_T-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene1","l3-o456-clear-olm22-medium-r1-20261019-swap_blocks-standard-s0-scene0","l3-o456-clear-generalization12-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.32916666666666666,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-align_blocks-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o456-clear-generalization12-20261019-v1-arrange_largest_number-random-s0-scene0","l3-o456-remainder12-20261026T213800-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-classify_objects-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-classify_objects-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-classify_objects_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-classify_objects_by_language-standard-s0-scene1"],"score":0.25,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-cover_blocks-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-fasten_screws-standard-s0-scene0","l3-o456-remainder12-20261026T213800-fasten_screws-standard-s0-scene1"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o456-clear-generalization12-20261019-v1-fold_clothes-random-s0-scene0","l3-o456-complement30-20261025-fold_clothes-standard-s0-scene0"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-general_pickup-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-imitate_sorting_sequence-standard-s0-scene0","l3-o456-o456-repaired-20261024T000632-e66c6663-imitate_sorting_sequence-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-o456-clear-precision4-20261018-v1-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-match_and_pick_from_conveyor-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o456-clear-generalization12-20261019-v1-pack_objects_into_box-random-s0-scene0","l3-o456-remainder12-20261026T213800-pack_objects_into_box-standard-s0-scene0"],"score":0.175,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-pick_from_conveyor_by_image-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-play_Xylophone-standard-s0-scene0","l3-o456-remainder12-20261026T213800-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o456-clear-precision4-20261018-v1-plug_in_charger-standard-s0-scene0","l3-o456-complement30-20261025-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-o456-clear-precision8-completion-20261019-v1-pour_balls_into_vase-standard-s0-scene0","l3-o456-complement30-20261025-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-press_by_number-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o456-clear-generalization12-20261019-v1-push_T-random-s0-scene0","l3-o456-remainder12-20261026T213800-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-put_bottles_into_dustbin-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-solve_equation-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o456-clear-generalization12-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-o456-complement30-20261025-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-stack_blocks_by_language-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-stack_blocks_by_language-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-o456-clear-generalization12-20261019-v1-stack_bowls-random-s0-scene0","l3-o456-remainder12-20261026T213800-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-swap_T-standard-s0-scene0","l3-o456-clear-olm22-medium-devset-20261020-swap_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-o456-clear-olm22-medium-r1-20261019-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-o456-clear-generalization12-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"e74a4b2bdf132b02ebec8150d04102ce8cbc2c883748d9e69ed36064602def1c","name":"persistent-cap20-o456-clear","selection_id":"l3-o456-clear-20261019"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.41041666666666665,"success_rate":0.375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2890625,"success_rate":0.21875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.7000000000000001,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.365625,"success_rate":0.34375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.228125,"success_rate":0.1875}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.3986458333333333,"selected_run_ids":["l3-r1-keyframes-precision8-20261019-v1-align_blocks-standard-s0-scene0","r1-dev69-20261030-00-align_blocks-standard-s0-scene1","r1-dev69-20261030-01-align_blocks-standard-s0-scene2","r1-dev69-20261030-02-align_blocks-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","r1-dev69-20261030-03-arrange_largest_number-standard-s0-scene0","r1-dev69-20261030-04-arrange_largest_number-random-s0-scene1","r1-dev69-20261030-05-arrange_largest_number-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-build_tower-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-classify_objects-standard-s0-scene0","r1-dev69-20261030-06-classify_objects-standard-s0-scene1","r1-dev69-20261030-07-classify_objects-standard-s0-scene2","r1-dev69-20261030-08-classify_objects-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","r1-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1","r1-dev69-20261030-10-classify_objects_by_language-standard-s0-scene2","r1-dev69-20261030-11-classify_objects_by_language-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-cover_blocks-standard-s0-scene0","r1-dev69-20261030-12-cover_blocks-standard-s0-scene1","r1-dev69-20261030-13-cover_blocks-standard-s0-scene2","r1-dev69-20261030-14-cover_blocks-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-deposit_coin-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-fasten_screws-standard-s0-scene0","r1-dev69-20261030-15-fasten_screws-standard-s0-scene1","r1-dev69-20261030-16-fasten_screws-standard-s0-scene2","r1-dev69-20261030-17-fasten_screws-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-fill_pen_holder-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-fold_clothes-random-s0-scene0","r1-dev69-20261030-18-fold_clothes-standard-s0-scene0","r1-dev69-20261030-19-fold_clothes-random-s0-scene1","r1-dev69-20261030-20-fold_clothes-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-holdretry1-general_pickup-standard-s0-scene0","r1-dev69-20261030-21-general_pickup-standard-s0-scene1","r1-dev69-20261030-22-general_pickup-standard-s0-scene2","r1-dev69-20261030-23-general_pickup-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-hang_mugs-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","r1-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1","r1-dev69-20261030-25-imitate_sorting_sequence-standard-s0-scene2","r1-dev69-20261030-26-imitate_sorting_sequence-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-insert_key-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-insert_tubes-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-make_kong-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-make_toast-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","r1-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1","r1-dev69-20261030-28-match_and_pick_from_conveyor-standard-s0-scene2","r1-dev69-20261030-29-match_and_pick_from_conveyor-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-organize_table-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","r1-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0","r1-dev69-20261030-31-pack_objects_into_box-random-s0-scene1","r1-dev69-20261030-32-pack_objects_into_box-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-holdretry1-pick_from_conveyor_by_image-standard-s0-scene0","r1-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1","r1-dev69-20261030-34-pick_from_conveyor_by_image-standard-s0-scene2","r1-dev69-20261030-35-pick_from_conveyor_by_image-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","r1-dev69-20261030-36-play_Xylophone-standard-s0-scene1","r1-dev69-20261030-37-play_Xylophone-standard-s0-scene2","r1-dev69-20261030-38-play_Xylophone-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","r1-dev69-20261030-39-plug_in_charger-standard-s0-scene1","r1-dev69-20261030-40-plug_in_charger-standard-s0-scene2","r1-dev69-20261030-41-plug_in_charger-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","r1-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1","r1-dev69-20261030-43-pour_balls_into_vase-standard-s0-scene2","r1-dev69-20261030-44-pour_balls_into_vase-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-pour_by_language-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-press_by_number-standard-s0-scene0","r1-dev69-20261030-45-press_by_number-standard-s0-scene1","r1-dev69-20261030-46-press_by_number-standard-s0-scene2","r1-dev69-20261030-47-press_by_number-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-push_T-random-s0-scene0","r1-dev69-20261030-48-push_T-standard-s0-scene0","r1-dev69-20261030-49-push_T-random-s0-scene1","r1-dev69-20261030-50-push_T-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","r1-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1","r1-dev69-20261030-52-put_bottles_into_dustbin-standard-s0-scene2","r1-dev69-20261030-53-put_bottles_into_dustbin-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-holdretry1-solve_equation-standard-s0-scene0","r1-dev69-20261030-54-solve_equation-standard-s0-scene1","r1-dev69-20261030-55-solve_equation-standard-s0-scene2","r1-dev69-20261030-56-solve_equation-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","r1-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0","r1-dev69-20261030-58-sort_nesting_dolls_by_size-random-s0-scene1","r1-dev69-20261030-59-sort_nesting_dolls_by_size-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-holdretry1-stack_blocks-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","r1-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1","r1-dev69-20261030-61-stack_blocks_by_language-standard-s0-scene2","r1-dev69-20261030-62-stack_blocks_by_language-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-stack_bowls-random-s0-scene0","r1-dev69-20261030-63-stack_bowls-standard-s0-scene0","r1-dev69-20261030-64-stack_bowls-random-s0-scene1","r1-dev69-20261030-65-stack_bowls-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_laptop_and_headphones-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_tools_in_toolbox-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-swap_T-standard-s0-scene0","r1-dev69-20261030-66-swap_T-standard-s0-scene1","r1-dev69-20261030-67-swap_T-standard-s0-scene2","r1-dev69-20261030-68-swap_T-standard-s0-scene3","l3-r1-keyframes-precision8-20261019-v1-swap_blocks-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3583333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-align_blocks-standard-s0-scene0","r1-dev69-20261030-00-align_blocks-standard-s0-scene1","r1-dev69-20261030-01-align_blocks-standard-s0-scene2","r1-dev69-20261030-02-align_blocks-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","r1-dev69-20261030-03-arrange_largest_number-standard-s0-scene0","r1-dev69-20261030-04-arrange_largest_number-random-s0-scene1","r1-dev69-20261030-05-arrange_largest_number-standard-s0-scene1"],"score":0.825,"success_rate":0.75,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-build_tower-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-classify_objects-standard-s0-scene0","r1-dev69-20261030-06-classify_objects-standard-s0-scene1","r1-dev69-20261030-07-classify_objects-standard-s0-scene2","r1-dev69-20261030-08-classify_objects-standard-s0-scene3"],"score":0.6,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","r1-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1","r1-dev69-20261030-10-classify_objects_by_language-standard-s0-scene2","r1-dev69-20261030-11-classify_objects_by_language-standard-s0-scene3"],"score":0.375,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-cover_blocks-standard-s0-scene0","r1-dev69-20261030-12-cover_blocks-standard-s0-scene1","r1-dev69-20261030-13-cover_blocks-standard-s0-scene2","r1-dev69-20261030-14-cover_blocks-standard-s0-scene3"],"score":0.575,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fasten_screws-standard-s0-scene0","r1-dev69-20261030-15-fasten_screws-standard-s0-scene1","r1-dev69-20261030-16-fasten_screws-standard-s0-scene2","r1-dev69-20261030-17-fasten_screws-standard-s0-scene3"],"score":0.425,"success_rate":0.25,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fold_clothes-random-s0-scene0","r1-dev69-20261030-18-fold_clothes-standard-s0-scene0","r1-dev69-20261030-19-fold_clothes-random-s0-scene1","r1-dev69-20261030-20-fold_clothes-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-general_pickup-standard-s0-scene0","r1-dev69-20261030-21-general_pickup-standard-s0-scene1","r1-dev69-20261030-22-general_pickup-standard-s0-scene2","r1-dev69-20261030-23-general_pickup-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","r1-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1","r1-dev69-20261030-25-imitate_sorting_sequence-standard-s0-scene2","r1-dev69-20261030-26-imitate_sorting_sequence-standard-s0-scene3"],"score":0.875,"success_rate":0.75,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","r1-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1","r1-dev69-20261030-28-match_and_pick_from_conveyor-standard-s0-scene2","r1-dev69-20261030-29-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-organize_table-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","r1-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0","r1-dev69-20261030-31-pack_objects_into_box-random-s0-scene1","r1-dev69-20261030-32-pack_objects_into_box-standard-s0-scene1"],"score":0.3125,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-pick_from_conveyor_by_image-standard-s0-scene0","r1-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1","r1-dev69-20261030-34-pick_from_conveyor_by_image-standard-s0-scene2","r1-dev69-20261030-35-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","r1-dev69-20261030-36-play_Xylophone-standard-s0-scene1","r1-dev69-20261030-37-play_Xylophone-standard-s0-scene2","r1-dev69-20261030-38-play_Xylophone-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","r1-dev69-20261030-39-plug_in_charger-standard-s0-scene1","r1-dev69-20261030-40-plug_in_charger-standard-s0-scene2","r1-dev69-20261030-41-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","r1-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1","r1-dev69-20261030-43-pour_balls_into_vase-standard-s0-scene2","r1-dev69-20261030-44-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-press_by_number-standard-s0-scene0","r1-dev69-20261030-45-press_by_number-standard-s0-scene1","r1-dev69-20261030-46-press_by_number-standard-s0-scene2","r1-dev69-20261030-47-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-push_T-random-s0-scene0","r1-dev69-20261030-48-push_T-standard-s0-scene0","r1-dev69-20261030-49-push_T-random-s0-scene1","r1-dev69-20261030-50-push_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","r1-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1","r1-dev69-20261030-52-put_bottles_into_dustbin-standard-s0-scene2","r1-dev69-20261030-53-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.5125,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-solve_equation-standard-s0-scene0","r1-dev69-20261030-54-solve_equation-standard-s0-scene1","r1-dev69-20261030-55-solve_equation-standard-s0-scene2","r1-dev69-20261030-56-solve_equation-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","r1-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0","r1-dev69-20261030-58-sort_nesting_dolls_by_size-random-s0-scene1","r1-dev69-20261030-59-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","r1-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1","r1-dev69-20261030-61-stack_blocks_by_language-standard-s0-scene2","r1-dev69-20261030-62-stack_blocks_by_language-standard-s0-scene3"],"score":0.8,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-stack_bowls-random-s0-scene0","r1-dev69-20261030-63-stack_bowls-standard-s0-scene0","r1-dev69-20261030-64-stack_bowls-random-s0-scene1","r1-dev69-20261030-65-stack_bowls-standard-s0-scene1"],"score":0.7875,"success_rate":0.75,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-swap_T-standard-s0-scene0","r1-dev69-20261030-66-swap_T-standard-s0-scene1","r1-dev69-20261030-67-swap_T-standard-s0-scene2","r1-dev69-20261030-68-swap_T-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.31666666666666665,"success_rate":0.25},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.18125,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.5,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.16875,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.36666666666666664,"selected_run_ids":["l3-r1-keyframes-precision8-20261019-v1-align_blocks-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-build_tower-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-classify_objects-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-cover_blocks-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-deposit_coin-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-fasten_screws-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-fill_pen_holder-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-fold_clothes-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-general_pickup-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-hang_mugs-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-insert_key-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-insert_tubes-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-make_kong-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-make_toast-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-organize_table-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-pick_from_conveyor_by_image-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-pour_by_language-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-press_by_number-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-push_T-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-solve_equation-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-stack_blocks-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-stack_bowls-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_laptop_and_headphones-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_tools_in_toolbox-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-swap_T-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-swap_blocks-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3333333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-arrange_largest_number-random-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-build_tower-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-classify_objects-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-organize_table-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-press_by_number-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-swap_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.41875,"success_rate":0.375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.290625,"success_rate":0.25},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6375000000000001,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.44375,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.21875,"success_rate":0.1875}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.401875,"selected_run_ids":["l3-r1-keyframes-precision8-20261019-v1-align_blocks-standard-s0-scene0","r1-dev69-20261030-00-align_blocks-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","r1-dev69-20261030-03-arrange_largest_number-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-build_tower-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-classify_objects-standard-s0-scene0","r1-dev69-20261030-06-classify_objects-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","r1-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-cover_blocks-standard-s0-scene0","r1-dev69-20261030-12-cover_blocks-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-deposit_coin-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-fasten_screws-standard-s0-scene0","r1-dev69-20261030-15-fasten_screws-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-fill_pen_holder-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-fold_clothes-random-s0-scene0","r1-dev69-20261030-18-fold_clothes-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-general_pickup-standard-s0-scene0","r1-dev69-20261030-21-general_pickup-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-hang_mugs-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","r1-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-insert_key-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-insert_tubes-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-make_kong-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-make_toast-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","r1-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-organize_table-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","r1-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-pick_from_conveyor_by_image-standard-s0-scene0","r1-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","r1-dev69-20261030-36-play_Xylophone-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","r1-dev69-20261030-39-plug_in_charger-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","r1-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-pour_by_language-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-press_by_number-standard-s0-scene0","r1-dev69-20261030-45-press_by_number-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-push_T-random-s0-scene0","r1-dev69-20261030-48-push_T-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","r1-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-holdretry1-solve_equation-standard-s0-scene0","r1-dev69-20261030-54-solve_equation-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","r1-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-stack_blocks-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","r1-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-stack_bowls-random-s0-scene0","r1-dev69-20261030-63-stack_bowls-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_laptop_and_headphones-random-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_tools_in_toolbox-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-swap_T-standard-s0-scene0","r1-dev69-20261030-66-swap_T-standard-s0-scene1","l3-r1-keyframes-precision8-20261019-v1-swap_blocks-standard-s0-scene0","l3-r1-keyframes-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3666666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-align_blocks-standard-s0-scene0","r1-dev69-20261030-00-align_blocks-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","r1-dev69-20261030-03-arrange_largest_number-standard-s0-scene0"],"score":0.65,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-build_tower-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-classify_objects-standard-s0-scene0","r1-dev69-20261030-06-classify_objects-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","r1-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1"],"score":0.55,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-cover_blocks-standard-s0-scene0","r1-dev69-20261030-12-cover_blocks-standard-s0-scene1"],"score":0.575,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fasten_screws-standard-s0-scene0","r1-dev69-20261030-15-fasten_screws-standard-s0-scene1"],"score":0.1,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-fold_clothes-random-s0-scene0","r1-dev69-20261030-18-fold_clothes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-general_pickup-standard-s0-scene0","r1-dev69-20261030-21-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","r1-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","r1-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-organize_table-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","r1-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0"],"score":0.375,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-pick_from_conveyor_by_image-standard-s0-scene0","r1-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","r1-dev69-20261030-36-play_Xylophone-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","r1-dev69-20261030-39-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","r1-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-press_by_number-standard-s0-scene0","r1-dev69-20261030-45-press_by_number-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-push_T-random-s0-scene0","r1-dev69-20261030-48-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","r1-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.625,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-solve_equation-standard-s0-scene0","r1-dev69-20261030-54-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","r1-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","r1-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-stack_bowls-random-s0-scene0","r1-dev69-20261030-63-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-holdretry1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-swap_T-standard-s0-scene0","r1-dev69-20261030-66-swap_T-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r1-keyframes-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"09c6b520fb9e4654614d6aedd6850562a1c82c2bf77af895e8eead3437f0868a","name":"persistent-cap20-r1","selection_id":"l3-r1-keyframes-precision8-20261019-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.403125,"success_rate":0.375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.28281249999999997,"success_rate":0.09375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5541666666666667,"success_rate":0.5416666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.403125,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.115625,"success_rate":0.0625}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.3517708333333333,"selected_run_ids":["l3-r2-precision8-20261019-v1-align_blocks-standard-s0-scene0","r2-dev69-20261030-00-align_blocks-standard-s0-scene1","r2-dev69-20261030-01-align_blocks-standard-s0-scene2","r2-dev69-20261030-02-align_blocks-standard-s0-scene3","l3-r2-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","r2-dev69-20261030-03-arrange_largest_number-standard-s0-scene0","r2-dev69-20261030-04-enospc-rerun1-arrange_largest_number-random-s0-scene1","r2-dev69-20261030-05-arrange_largest_number-standard-s0-scene1","l3-r2-precision8-20261019-v1-build_tower-standard-s0-scene0","l3-r2-precision8-20261019-v1-classify_objects-standard-s0-scene0","r2-dev69-20261030-06-classify_objects-standard-s0-scene1","r2-dev69-20261030-07-classify_objects-standard-s0-scene2","r2-dev69-20261030-08-classify_objects-standard-s0-scene3","l3-r2-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","r2-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1","r2-dev69-20261030-10-classify_objects_by_language-standard-s0-scene2","r2-dev69-20261030-11-classify_objects_by_language-standard-s0-scene3","l3-r2-precision8-20261019-v1-cover_blocks-standard-s0-scene0","r2-dev69-20261030-12-cover_blocks-standard-s0-scene1","r2-dev69-20261030-13-cover_blocks-standard-s0-scene2","r2-dev69-20261030-14-cover_blocks-standard-s0-scene3","l3-r2-precision8-20261019-v1-deposit_coin-standard-s0-scene0","l3-r2-precision8-20261019-v1-fasten_screws-standard-s0-scene0","r2-dev69-20261030-15-fasten_screws-standard-s0-scene1","r2-dev69-20261030-16-fasten_screws-standard-s0-scene2","r2-dev69-20261030-17-fasten_screws-standard-s0-scene3","l3-r2-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0","l3-r2-precision8-20261019-v1-fill_pen_holder-standard-s0-scene0","l3-r2-precision8-20261019-v1-fold_clothes-random-s0-scene0","r2-dev69-20261030-18-fold_clothes-standard-s0-scene0","r2-dev69-20261030-19-enospc-rerun1-fold_clothes-random-s0-scene1","r2-dev69-20261030-20-fold_clothes-standard-s0-scene1","l3-r2-precision8-20261019-v1-general_pickup-standard-s0-scene0","r2-dev69-20261030-21-general_pickup-standard-s0-scene1","r2-dev69-20261030-22-general_pickup-standard-s0-scene2","r2-dev69-20261030-23-general_pickup-standard-s0-scene3","l3-r2-precision8-20261019-v1-hang_mugs-random-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","r2-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1","r2-dev69-20261030-25-enospc-rerun1-imitate_sorting_sequence-standard-s0-scene2","r2-dev69-20261030-26-imitate_sorting_sequence-standard-s0-scene3","l3-r2-precision8-20261019-v1-insert_key-standard-s0-scene0","l3-r2-precision8-20261019-v1-insert_tubes-standard-s0-scene0","l3-r2-precision8-20261019-v1-make_kong-standard-s0-scene0","l3-r2-precision8-20261019-v1-make_toast-random-s0-scene0","l3-r2-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","r2-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1","r2-dev69-20261030-28-match_and_pick_from_conveyor-standard-s0-scene2","r2-dev69-20261030-29-match_and_pick_from_conveyor-standard-s0-scene3","l3-r2-precision8-20261019-v1-organize_table-standard-s0-scene0","l3-r2-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","r2-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0","r2-dev69-20261030-31-enospc-rerun1-pack_objects_into_box-random-s0-scene1","r2-dev69-20261030-32-pack_objects_into_box-standard-s0-scene1","l3-r2-precision8-20261019-v1-pick_from_conveyor_by_image-standard-s0-scene0","r2-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1","r2-dev69-20261030-34-enospc-rerun1-pick_from_conveyor_by_image-standard-s0-scene2","r2-dev69-20261030-35-pick_from_conveyor_by_image-standard-s0-scene3","l3-r2-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","r2-dev69-20261030-36-play_Xylophone-standard-s0-scene1","r2-dev69-20261030-37-play_Xylophone-standard-s0-scene2","r2-dev69-20261030-38-play_Xylophone-standard-s0-scene3","l3-r2-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0","l3-r2-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0","l3-r2-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","r2-dev69-20261030-39-plug_in_charger-standard-s0-scene1","r2-dev69-20261030-40-plug_in_charger-standard-s0-scene2","r2-dev69-20261030-41-plug_in_charger-standard-s0-scene3","l3-r2-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","r2-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1","r2-dev69-20261030-43-pour_balls_into_vase-standard-s0-scene2","r2-dev69-20261030-44-pour_balls_into_vase-standard-s0-scene3","l3-r2-precision8-20261019-v1-pour_by_language-standard-s0-scene0","l3-r2-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-press_by_number-standard-s0-scene0","r2-dev69-20261030-45-press_by_number-standard-s0-scene1","r2-dev69-20261030-46-press_by_number-standard-s0-scene2","r2-dev69-20261030-47-press_by_number-standard-s0-scene3","l3-r2-precision8-20261019-v1-push_T-random-s0-scene0","r2-dev69-20261030-48-push_T-standard-s0-scene0","r2-dev69-20261030-49-push_T-random-s0-scene1","r2-dev69-20261030-50-push_T-standard-s0-scene1","l3-r2-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","r2-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1","r2-dev69-20261030-52-put_bottles_into_dustbin-standard-s0-scene2","r2-dev69-20261030-53-put_bottles_into_dustbin-standard-s0-scene3","l3-r2-precision8-20261019-v1-solve_equation-standard-s0-scene0","r2-dev69-20261030-54-solve_equation-standard-s0-scene1","r2-dev69-20261030-55-solve_equation-standard-s0-scene2","r2-dev69-20261030-56-solve_equation-standard-s0-scene3","l3-r2-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","r2-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0","r2-dev69-20261030-58-sort_nesting_dolls_by_size-random-s0-scene1","r2-dev69-20261030-59-sort_nesting_dolls_by_size-standard-s0-scene1","l3-r2-precision8-20261019-v1-stack_blocks-random-s0-scene0","l3-r2-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","r2-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1","r2-dev69-20261030-61-stack_blocks_by_language-standard-s0-scene2","r2-dev69-20261030-62-stack_blocks_by_language-standard-s0-scene3","l3-r2-precision8-20261019-v1-stack_bowls-random-s0-scene0","r2-dev69-20261030-63-stack_bowls-standard-s0-scene0","r2-dev69-20261030-64-stack_bowls-random-s0-scene1","r2-dev69-20261030-65-stack_bowls-standard-s0-scene1","l3-r2-precision8-20261019-v1-store_laptop_and_headphones-random-s0-scene0","l3-r2-precision8-20261019-v1-store_tools_in_toolbox-standard-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-swap_T-standard-s0-scene0","r2-dev69-20261030-66-swap_T-standard-s0-scene1","r2-dev69-20261030-67-swap_T-standard-s0-scene2","r2-dev69-20261030-68-swap_T-standard-s0-scene3","l3-r2-precision8-20261019-v1-swap_blocks-standard-s0-scene0","l3-r2-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2895833333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-align_blocks-standard-s0-scene0","r2-dev69-20261030-00-align_blocks-standard-s0-scene1","r2-dev69-20261030-01-align_blocks-standard-s0-scene2","r2-dev69-20261030-02-align_blocks-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","r2-dev69-20261030-03-arrange_largest_number-standard-s0-scene0","r2-dev69-20261030-04-enospc-rerun1-arrange_largest_number-random-s0-scene1","r2-dev69-20261030-05-arrange_largest_number-standard-s0-scene1"],"score":0.6375,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-classify_objects-standard-s0-scene0","r2-dev69-20261030-06-classify_objects-standard-s0-scene1","r2-dev69-20261030-07-classify_objects-standard-s0-scene2","r2-dev69-20261030-08-classify_objects-standard-s0-scene3"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","r2-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1","r2-dev69-20261030-10-classify_objects_by_language-standard-s0-scene2","r2-dev69-20261030-11-classify_objects_by_language-standard-s0-scene3"],"score":0.47500000000000003,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-cover_blocks-standard-s0-scene0","r2-dev69-20261030-12-cover_blocks-standard-s0-scene1","r2-dev69-20261030-13-cover_blocks-standard-s0-scene2","r2-dev69-20261030-14-cover_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-fasten_screws-standard-s0-scene0","r2-dev69-20261030-15-fasten_screws-standard-s0-scene1","r2-dev69-20261030-16-fasten_screws-standard-s0-scene2","r2-dev69-20261030-17-fasten_screws-standard-s0-scene3"],"score":0.425,"success_rate":0.25,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-fold_clothes-random-s0-scene0","r2-dev69-20261030-18-fold_clothes-standard-s0-scene0","r2-dev69-20261030-19-enospc-rerun1-fold_clothes-random-s0-scene1","r2-dev69-20261030-20-fold_clothes-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-general_pickup-standard-s0-scene0","r2-dev69-20261030-21-general_pickup-standard-s0-scene1","r2-dev69-20261030-22-general_pickup-standard-s0-scene2","r2-dev69-20261030-23-general_pickup-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","r2-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1","r2-dev69-20261030-25-enospc-rerun1-imitate_sorting_sequence-standard-s0-scene2","r2-dev69-20261030-26-imitate_sorting_sequence-standard-s0-scene3"],"score":0.575,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","r2-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1","r2-dev69-20261030-28-match_and_pick_from_conveyor-standard-s0-scene2","r2-dev69-20261030-29-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","r2-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0","r2-dev69-20261030-31-enospc-rerun1-pack_objects_into_box-random-s0-scene1","r2-dev69-20261030-32-pack_objects_into_box-standard-s0-scene1"],"score":0.8125,"success_rate":0.75,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-pick_from_conveyor_by_image-standard-s0-scene0","r2-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1","r2-dev69-20261030-34-enospc-rerun1-pick_from_conveyor_by_image-standard-s0-scene2","r2-dev69-20261030-35-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","r2-dev69-20261030-36-play_Xylophone-standard-s0-scene1","r2-dev69-20261030-37-play_Xylophone-standard-s0-scene2","r2-dev69-20261030-38-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","r2-dev69-20261030-39-plug_in_charger-standard-s0-scene1","r2-dev69-20261030-40-plug_in_charger-standard-s0-scene2","r2-dev69-20261030-41-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","r2-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1","r2-dev69-20261030-43-pour_balls_into_vase-standard-s0-scene2","r2-dev69-20261030-44-pour_balls_into_vase-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-press_by_number-standard-s0-scene0","r2-dev69-20261030-45-press_by_number-standard-s0-scene1","r2-dev69-20261030-46-press_by_number-standard-s0-scene2","r2-dev69-20261030-47-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-push_T-random-s0-scene0","r2-dev69-20261030-48-push_T-standard-s0-scene0","r2-dev69-20261030-49-push_T-random-s0-scene1","r2-dev69-20261030-50-push_T-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","r2-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1","r2-dev69-20261030-52-put_bottles_into_dustbin-standard-s0-scene2","r2-dev69-20261030-53-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.5125,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-solve_equation-standard-s0-scene0","r2-dev69-20261030-54-solve_equation-standard-s0-scene1","r2-dev69-20261030-55-solve_equation-standard-s0-scene2","r2-dev69-20261030-56-solve_equation-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","r2-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0","r2-dev69-20261030-58-sort_nesting_dolls_by_size-random-s0-scene1","r2-dev69-20261030-59-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","r2-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1","r2-dev69-20261030-61-stack_blocks_by_language-standard-s0-scene2","r2-dev69-20261030-62-stack_blocks_by_language-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-stack_bowls-random-s0-scene0","r2-dev69-20261030-63-stack_bowls-standard-s0-scene0","r2-dev69-20261030-64-stack_bowls-random-s0-scene1","r2-dev69-20261030-65-stack_bowls-standard-s0-scene1"],"score":0.7875,"success_rate":0.75,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-swap_T-standard-s0-scene0","r2-dev69-20261030-66-swap_T-standard-s0-scene1","r2-dev69-20261030-67-swap_T-standard-s0-scene2","r2-dev69-20261030-68-swap_T-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.2791666666666667,"success_rate":0.25},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2125,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.5,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.03125,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.33791666666666664,"selected_run_ids":["l3-r2-precision8-20261019-v1-align_blocks-standard-s0-scene0","l3-r2-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","l3-r2-precision8-20261019-v1-build_tower-standard-s0-scene0","l3-r2-precision8-20261019-v1-classify_objects-standard-s0-scene0","l3-r2-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","l3-r2-precision8-20261019-v1-cover_blocks-standard-s0-scene0","l3-r2-precision8-20261019-v1-deposit_coin-standard-s0-scene0","l3-r2-precision8-20261019-v1-fasten_screws-standard-s0-scene0","l3-r2-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0","l3-r2-precision8-20261019-v1-fill_pen_holder-standard-s0-scene0","l3-r2-precision8-20261019-v1-fold_clothes-random-s0-scene0","l3-r2-precision8-20261019-v1-general_pickup-standard-s0-scene0","l3-r2-precision8-20261019-v1-hang_mugs-random-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","l3-r2-precision8-20261019-v1-insert_key-standard-s0-scene0","l3-r2-precision8-20261019-v1-insert_tubes-standard-s0-scene0","l3-r2-precision8-20261019-v1-make_kong-standard-s0-scene0","l3-r2-precision8-20261019-v1-make_toast-random-s0-scene0","l3-r2-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","l3-r2-precision8-20261019-v1-organize_table-standard-s0-scene0","l3-r2-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","l3-r2-precision8-20261019-v1-pick_from_conveyor_by_image-standard-s0-scene0","l3-r2-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","l3-r2-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0","l3-r2-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0","l3-r2-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","l3-r2-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","l3-r2-precision8-20261019-v1-pour_by_language-standard-s0-scene0","l3-r2-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-press_by_number-standard-s0-scene0","l3-r2-precision8-20261019-v1-push_T-random-s0-scene0","l3-r2-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","l3-r2-precision8-20261019-v1-solve_equation-standard-s0-scene0","l3-r2-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","l3-r2-precision8-20261019-v1-stack_blocks-random-s0-scene0","l3-r2-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","l3-r2-precision8-20261019-v1-stack_bowls-random-s0-scene0","l3-r2-precision8-20261019-v1-store_laptop_and_headphones-random-s0-scene0","l3-r2-precision8-20261019-v1-store_tools_in_toolbox-standard-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-swap_T-standard-s0-scene0","l3-r2-precision8-20261019-v1-swap_blocks-standard-s0-scene0","l3-r2-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2833333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-arrange_largest_number-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-fasten_screws-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.38958333333333334,"success_rate":0.375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.259375,"success_rate":0.0625},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6791666666666667,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.4625,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.0625,"success_rate":0.0}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.37062500000000004,"selected_run_ids":["l3-r2-precision8-20261019-v1-align_blocks-standard-s0-scene0","r2-dev69-20261030-00-align_blocks-standard-s0-scene1","l3-r2-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","r2-dev69-20261030-03-arrange_largest_number-standard-s0-scene0","l3-r2-precision8-20261019-v1-build_tower-standard-s0-scene0","l3-r2-precision8-20261019-v1-classify_objects-standard-s0-scene0","r2-dev69-20261030-06-classify_objects-standard-s0-scene1","l3-r2-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","r2-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1","l3-r2-precision8-20261019-v1-cover_blocks-standard-s0-scene0","r2-dev69-20261030-12-cover_blocks-standard-s0-scene1","l3-r2-precision8-20261019-v1-deposit_coin-standard-s0-scene0","l3-r2-precision8-20261019-v1-fasten_screws-standard-s0-scene0","r2-dev69-20261030-15-fasten_screws-standard-s0-scene1","l3-r2-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0","l3-r2-precision8-20261019-v1-fill_pen_holder-standard-s0-scene0","l3-r2-precision8-20261019-v1-fold_clothes-random-s0-scene0","r2-dev69-20261030-18-fold_clothes-standard-s0-scene0","l3-r2-precision8-20261019-v1-general_pickup-standard-s0-scene0","r2-dev69-20261030-21-general_pickup-standard-s0-scene1","l3-r2-precision8-20261019-v1-hang_mugs-random-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","r2-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1","l3-r2-precision8-20261019-v1-insert_key-standard-s0-scene0","l3-r2-precision8-20261019-v1-insert_tubes-standard-s0-scene0","l3-r2-precision8-20261019-v1-make_kong-standard-s0-scene0","l3-r2-precision8-20261019-v1-make_toast-random-s0-scene0","l3-r2-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","r2-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1","l3-r2-precision8-20261019-v1-organize_table-standard-s0-scene0","l3-r2-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","r2-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0","l3-r2-precision8-20261019-v1-pick_from_conveyor_by_image-standard-s0-scene0","r2-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1","l3-r2-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","r2-dev69-20261030-36-play_Xylophone-standard-s0-scene1","l3-r2-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0","l3-r2-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0","l3-r2-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","r2-dev69-20261030-39-plug_in_charger-standard-s0-scene1","l3-r2-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","r2-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1","l3-r2-precision8-20261019-v1-pour_by_language-standard-s0-scene0","l3-r2-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-press_by_number-standard-s0-scene0","r2-dev69-20261030-45-press_by_number-standard-s0-scene1","l3-r2-precision8-20261019-v1-push_T-random-s0-scene0","r2-dev69-20261030-48-push_T-standard-s0-scene0","l3-r2-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","r2-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1","l3-r2-precision8-20261019-v1-solve_equation-standard-s0-scene0","r2-dev69-20261030-54-solve_equation-standard-s0-scene1","l3-r2-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","r2-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0","l3-r2-precision8-20261019-v1-stack_blocks-random-s0-scene0","l3-r2-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","r2-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1","l3-r2-precision8-20261019-v1-stack_bowls-random-s0-scene0","r2-dev69-20261030-63-stack_bowls-standard-s0-scene0","l3-r2-precision8-20261019-v1-store_laptop_and_headphones-random-s0-scene0","l3-r2-precision8-20261019-v1-store_tools_in_toolbox-standard-s0-scene0","l3-r2-precision8-20261019-v1-holdretry1-swap_T-standard-s0-scene0","r2-dev69-20261030-66-swap_T-standard-s0-scene1","l3-r2-precision8-20261019-v1-swap_blocks-standard-s0-scene0","l3-r2-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3083333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-align_blocks-standard-s0-scene0","r2-dev69-20261030-00-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-arrange_largest_number-random-s0-scene0","r2-dev69-20261030-03-arrange_largest_number-standard-s0-scene0"],"score":0.575,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-classify_objects-standard-s0-scene0","r2-dev69-20261030-06-classify_objects-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-classify_objects_by_language-standard-s0-scene0","r2-dev69-20261030-09-classify_objects_by_language-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-cover_blocks-standard-s0-scene0","r2-dev69-20261030-12-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-fasten_screws-standard-s0-scene0","r2-dev69-20261030-15-fasten_screws-standard-s0-scene1"],"score":0.25,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-fill_egg_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-fold_clothes-random-s0-scene0","r2-dev69-20261030-18-fold_clothes-standard-s0-scene0"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-general_pickup-standard-s0-scene0","r2-dev69-20261030-21-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-imitate_sorting_sequence-standard-s0-scene0","r2-dev69-20261030-24-imitate_sorting_sequence-standard-s0-scene1"],"score":0.575,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-match_and_pick_from_conveyor-standard-s0-scene0","r2-dev69-20261030-27-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-pack_objects_into_box-random-s0-scene0","r2-dev69-20261030-30-pack_objects_into_box-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-pick_from_conveyor_by_image-standard-s0-scene0","r2-dev69-20261030-33-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-play_Xylophone-standard-s0-scene0","r2-dev69-20261030-36-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-plug_in_charger-standard-s0-scene0","r2-dev69-20261030-39-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-pour_balls_into_vase-standard-s0-scene0","r2-dev69-20261030-42-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-press_by_number-standard-s0-scene0","r2-dev69-20261030-45-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-push_T-random-s0-scene0","r2-dev69-20261030-48-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-put_bottles_into_dustbin-standard-s0-scene0","r2-dev69-20261030-51-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.325,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-solve_equation-standard-s0-scene0","r2-dev69-20261030-54-solve_equation-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-sort_nesting_dolls_by_size-random-s0-scene0","r2-dev69-20261030-57-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-stack_blocks_by_language-standard-s0-scene0","r2-dev69-20261030-60-stack_blocks_by_language-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-stack_bowls-random-s0-scene0","r2-dev69-20261030-63-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-r2-precision8-20261019-v1-holdretry1-swap_T-standard-s0-scene0","r2-dev69-20261030-66-swap_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-r2-precision8-20261019-v1-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"77b8e442594ab39c212d292906aab6a84cc9375ad9b80e810362641d4ee90c1c","name":"persistent-cap20-r2","selection_id":"l3-r2-precision8-20261019-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.403125,"success_rate":0.3958333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2875,"success_rate":0.09375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5291666666666667,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.39375,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.053125,"success_rate":0.0}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.33333333333333337,"selected_run_ids":["l3-low-mixed42-20261012-align_blocks-standard-s0-scene0","l3-low-r2-mixed42-20261013-align_blocks-standard-s0-scene1","l3-low-r3-mixed42-20261013-align_blocks-standard-s0-scene2","l3-low-r4-mixed42-20261013-align_blocks-standard-s0-scene3","l3-low-mixed42-20261012-arrange_largest_number-random-s0-scene0","l3-low-r2-mixed42-20261013-arrange_largest_number-standard-s0-scene0","l3-low-r3-mixed42-20261013-arrange_largest_number-random-s0-scene1","l3-low-r4-mixed42-20261013-arrange_largest_number-standard-s0-scene1","l3-low-mixed42-20261012-init-video3-build_tower-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-classify_objects-standard-s0-scene0","l3-low-r2-mixed42-20261013-classify_objects-standard-s0-scene1","l3-low-r3-mixed42-20261013-classify_objects-standard-s0-scene2","l3-low-r4-infra72retry1-20261014-classify_objects-standard-s0-scene3","l3-low-mixed42-20261012-classify_objects_by_language-standard-s0-scene0","l3-low-r2-mixed42-20261013-classify_objects_by_language-standard-s0-scene1","l3-low-r3-mixed42-20261013-classify_objects_by_language-standard-s0-scene2","l3-low-r4-mixed42-20261013-classify_objects_by_language-standard-s0-scene3","l3-low-mixed42-20261012-cover_blocks-standard-s0-scene0","l3-low-r2-mixed42-20261013-cover_blocks-standard-s0-scene1","l3-low-r3-mixed42-20261013-cover_blocks-standard-s0-scene2","l3-low-r4-mixed42-20261013-cover_blocks-standard-s0-scene3","l3-low-mixed42-20261012-deposit_coin-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-fasten_screws-standard-s0-scene0","l3-low-r2-mixed42-20261013-fasten_screws-standard-s0-scene1","l3-low-r3-mixed42-20261013-fasten_screws-standard-s0-scene2","l3-low-r4-mixed42-20261013-fasten_screws-standard-s0-scene3","l3-low-mixed42-20261012-init-repair2-fill_egg_holder-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-fill_pen_holder-standard-s0-scene0","l3-low-mixed42-20261012-fold_clothes-random-s0-scene0","l3-low-r2-mixed42-20261013-fold_clothes-standard-s0-scene0","l3-low-r3-mixed42-20261013-fold_clothes-random-s0-scene1","l3-low-r4-mixed42-20261013-fold_clothes-standard-s0-scene1","l3-low-mixed42-20261012-general_pickup-standard-s0-scene0","l3-low-r2-mixed42-20261013-general_pickup-standard-s0-scene1","l3-low-r3-mixed42-20261013-general_pickup-standard-s0-scene2","l3-low-r4-mixed42-20261013-general_pickup-standard-s0-scene3","l3-low-mixed42-20261012-hang_mugs-random-s0-scene0","l3-low-mixed42-20261012-imitate_sorting_sequence-standard-s0-scene0","l3-low-r2-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene1","l3-low-r3-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene2","l3-low-r4-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene3","l3-low-mixed42-20261012-insert_key-standard-s0-scene0","l3-low-mixed42-20261012-insert_tubes-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-make_kong-standard-s0-scene0","l3-low-mixed42-20261012-make_toast-random-s0-scene0","l3-low-mixed42-20261012-match_and_pick_from_conveyor-standard-s0-scene0","l3-low-r2-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene1","l3-low-r3-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene2","l3-low-r4-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene3","l3-low-mixed42-20261012-init-repair2-organize_table-standard-s0-scene0","l3-low-mixed42-20261012-pack_objects_into_box-random-s0-scene0","l3-low-r2-mixed42-20261013-pack_objects_into_box-standard-s0-scene0","l3-low-r3-mixed42-20261013-pack_objects_into_box-random-s0-scene1","l3-low-r4-mixed42-20261013-pack_objects_into_box-standard-s0-scene1","l3-low-mixed42-20261012-pick_from_conveyor_by_image-standard-s0-scene0","l3-low-r2-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene1","l3-low-r3-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene2","l3-low-r4-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene3","l3-low-mixed42-20261012-play_Xylophone-standard-s0-scene0","l3-low-r2-mixed42-20261013-play_Xylophone-standard-s0-scene1","l3-low-r3-mixed42-20261013-play_Xylophone-standard-s0-scene2","l3-low-r4-mixed42-20261013-play_Xylophone-standard-s0-scene3","l3-low-mixed42-20261012-play_stacking_toy-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-play_tic_tac_toe-standard-s0-scene0","l3-low-mixed42-20261012-plug_in_charger-standard-s0-scene0","l3-low-r2-mixed42-20261013-plug_in_charger-standard-s0-scene1","l3-low-r3-mixed42-20261013-plug_in_charger-standard-s0-scene2","l3-low-r4-mixed42-20261013-plug_in_charger-standard-s0-scene3","l3-low-mixed42-20261012-pour_balls_into_vase-standard-s0-scene0","l3-low-r2-mixed42-20261013-pour_balls_into_vase-standard-s0-scene1","l3-low-r3-mixed42-20261013-pour_balls_into_vase-standard-s0-scene2","l3-low-r4-mixed42-20261013-pour_balls_into_vase-standard-s0-scene3","l3-low-mixed42-20261012-pour_by_language-standard-s0-scene0","l3-low-mixed42-20261012-pour_liquid_into_cup-random-s0-scene0","l3-low-mixed42-20261012-press_by_number-standard-s0-scene0","l3-low-r2-mixed42-20261013-press_by_number-standard-s0-scene1","l3-low-r3-mixed42-20261013-press_by_number-standard-s0-scene2","l3-low-r4-mixed42-20261013-press_by_number-standard-s0-scene3","l3-low-mixed42-20261012-init-retry1-push_T-random-s0-scene0","l3-low-r2-mixed42-20261013-push_T-standard-s0-scene0","l3-low-r3-mixed42-20261013-push_T-random-s0-scene1","l3-low-r4-mixed42-20261013-push_T-standard-s0-scene1","l3-low-mixed42-20261012-init-repair2-put_bottles_into_dustbin-standard-s0-scene0","l3-low-r2-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene1","l3-low-r3-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene2","l3-low-r4-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene3","l3-low-mixed42-20261012-solve_equation-standard-s0-scene0","l3-low-r2-mixed42-20261013-solve_equation-standard-s0-scene1","l3-low-r3-mixed42-20261013-solve_equation-standard-s0-scene2","l3-low-r4-mixed42-20261013-solve_equation-standard-s0-scene3","l3-low-mixed42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","l3-low-r2-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene0","l3-low-r3-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene1","l3-low-r4-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene1","l3-low-mixed42-20261012-init-repair2-stack_blocks-random-s0-scene0","l3-low-mixed42-20261012-stack_blocks_by_language-standard-s0-scene0","l3-low-r2-mixed42-20261013-stack_blocks_by_language-standard-s0-scene1","l3-low-r3-mixed42-20261013-stack_blocks_by_language-standard-s0-scene2","l3-low-r4-mixed42-20261013-stack_blocks_by_language-standard-s0-scene3","l3_low_stack_bowls_random_s0_scene0_20261012","l3-low-r2-mixed42-20261013-stack_bowls-standard-s0-scene0","l3-low-r3-mixed42-20261013-stack_bowls-random-s0-scene1","l3-low-r4-mixed42-20261013-stack_bowls-standard-s0-scene1","l3-low-mixed42-20261012-init-video3-store_laptop_and_headphones-random-s0-scene0","l3-low-mixed42-20261012-store_tools_in_toolbox-standard-s0-scene0","l3-low-mixed42-20261012-swap_T-standard-s0-scene0","l3-low-r2-mixed42-20261013-swap_T-standard-s0-scene1","l3-low-r3-mixed42-20261013-swap_T-standard-s0-scene2","l3-low-r4-mixed42-20261013-swap_T-standard-s0-scene3","l3-low-mixed42-20261012-swap_blocks-standard-s0-scene0","l3-low-mixed42-20261012-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.27291666666666664,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-align_blocks-standard-s0-scene0","l3-low-r2-mixed42-20261013-align_blocks-standard-s0-scene1","l3-low-r3-mixed42-20261013-align_blocks-standard-s0-scene2","l3-low-r4-mixed42-20261013-align_blocks-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-arrange_largest_number-random-s0-scene0","l3-low-r2-mixed42-20261013-arrange_largest_number-standard-s0-scene0","l3-low-r3-mixed42-20261013-arrange_largest_number-random-s0-scene1","l3-low-r4-mixed42-20261013-arrange_largest_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-video3-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-init-repair2-classify_objects-standard-s0-scene0","l3-low-r2-mixed42-20261013-classify_objects-standard-s0-scene1","l3-low-r3-mixed42-20261013-classify_objects-standard-s0-scene2","l3-low-r4-infra72retry1-20261014-classify_objects-standard-s0-scene3"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-classify_objects_by_language-standard-s0-scene0","l3-low-r2-mixed42-20261013-classify_objects_by_language-standard-s0-scene1","l3-low-r3-mixed42-20261013-classify_objects_by_language-standard-s0-scene2","l3-low-r4-mixed42-20261013-classify_objects_by_language-standard-s0-scene3"],"score":0.55,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-cover_blocks-standard-s0-scene0","l3-low-r2-mixed42-20261013-cover_blocks-standard-s0-scene1","l3-low-r3-mixed42-20261013-cover_blocks-standard-s0-scene2","l3-low-r4-mixed42-20261013-cover_blocks-standard-s0-scene3"],"score":0.7875,"success_rate":0.75,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-init-repair2-fasten_screws-standard-s0-scene0","l3-low-r2-mixed42-20261013-fasten_screws-standard-s0-scene1","l3-low-r3-mixed42-20261013-fasten_screws-standard-s0-scene2","l3-low-r4-mixed42-20261013-fasten_screws-standard-s0-scene3"],"score":0.175,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-fold_clothes-random-s0-scene0","l3-low-r2-mixed42-20261013-fold_clothes-standard-s0-scene0","l3-low-r3-mixed42-20261013-fold_clothes-random-s0-scene1","l3-low-r4-mixed42-20261013-fold_clothes-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-general_pickup-standard-s0-scene0","l3-low-r2-mixed42-20261013-general_pickup-standard-s0-scene1","l3-low-r3-mixed42-20261013-general_pickup-standard-s0-scene2","l3-low-r4-mixed42-20261013-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-imitate_sorting_sequence-standard-s0-scene0","l3-low-r2-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene1","l3-low-r3-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene2","l3-low-r4-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene3"],"score":0.6375,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-match_and_pick_from_conveyor-standard-s0-scene0","l3-low-r2-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene1","l3-low-r3-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene2","l3-low-r4-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-pack_objects_into_box-random-s0-scene0","l3-low-r2-mixed42-20261013-pack_objects_into_box-standard-s0-scene0","l3-low-r3-mixed42-20261013-pack_objects_into_box-random-s0-scene1","l3-low-r4-mixed42-20261013-pack_objects_into_box-standard-s0-scene1"],"score":0.3,"success_rate":0.25,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-pick_from_conveyor_by_image-standard-s0-scene0","l3-low-r2-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene1","l3-low-r3-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene2","l3-low-r4-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-play_Xylophone-standard-s0-scene0","l3-low-r2-mixed42-20261013-play_Xylophone-standard-s0-scene1","l3-low-r3-mixed42-20261013-play_Xylophone-standard-s0-scene2","l3-low-r4-mixed42-20261013-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-plug_in_charger-standard-s0-scene0","l3-low-r2-mixed42-20261013-plug_in_charger-standard-s0-scene1","l3-low-r3-mixed42-20261013-plug_in_charger-standard-s0-scene2","l3-low-r4-mixed42-20261013-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-pour_balls_into_vase-standard-s0-scene0","l3-low-r2-mixed42-20261013-pour_balls_into_vase-standard-s0-scene1","l3-low-r3-mixed42-20261013-pour_balls_into_vase-standard-s0-scene2","l3-low-r4-mixed42-20261013-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-press_by_number-standard-s0-scene0","l3-low-r2-mixed42-20261013-press_by_number-standard-s0-scene1","l3-low-r3-mixed42-20261013-press_by_number-standard-s0-scene2","l3-low-r4-mixed42-20261013-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-init-retry1-push_T-random-s0-scene0","l3-low-r2-mixed42-20261013-push_T-standard-s0-scene0","l3-low-r3-mixed42-20261013-push_T-random-s0-scene1","l3-low-r4-mixed42-20261013-push_T-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-init-repair2-put_bottles_into_dustbin-standard-s0-scene0","l3-low-r2-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene1","l3-low-r3-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene2","l3-low-r4-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-solve_equation-standard-s0-scene0","l3-low-r2-mixed42-20261013-solve_equation-standard-s0-scene1","l3-low-r3-mixed42-20261013-solve_equation-standard-s0-scene2","l3-low-r4-mixed42-20261013-solve_equation-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","l3-low-r2-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene0","l3-low-r3-mixed42-20261013-sort_nesting_dolls_by_size-random-s0-scene1","l3-low-r4-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-stack_blocks_by_language-standard-s0-scene0","l3-low-r2-mixed42-20261013-stack_blocks_by_language-standard-s0-scene1","l3-low-r3-mixed42-20261013-stack_blocks_by_language-standard-s0-scene2","l3-low-r4-mixed42-20261013-stack_blocks_by_language-standard-s0-scene3"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3_low_stack_bowls_random_s0_scene0_20261012","l3-low-r2-mixed42-20261013-stack_bowls-standard-s0-scene0","l3-low-r3-mixed42-20261013-stack_bowls-random-s0-scene1","l3-low-r4-mixed42-20261013-stack_bowls-standard-s0-scene1"],"score":0.5375,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-video3-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3-low-mixed42-20261012-swap_T-standard-s0-scene0","l3-low-r2-mixed42-20261013-swap_T-standard-s0-scene1","l3-low-r3-mixed42-20261013-swap_T-standard-s0-scene2","l3-low-r4-mixed42-20261013-swap_T-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.5,"success_rate":0.5},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.30625,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5833333333333334,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.375,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.03125,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.3591666666666667,"selected_run_ids":["l3-low-mixed42-20261012-align_blocks-standard-s0-scene0","l3-low-mixed42-20261012-arrange_largest_number-random-s0-scene0","l3-low-mixed42-20261012-init-video3-build_tower-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-classify_objects-standard-s0-scene0","l3-low-mixed42-20261012-classify_objects_by_language-standard-s0-scene0","l3-low-mixed42-20261012-cover_blocks-standard-s0-scene0","l3-low-mixed42-20261012-deposit_coin-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-fasten_screws-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-fill_egg_holder-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-fill_pen_holder-standard-s0-scene0","l3-low-mixed42-20261012-fold_clothes-random-s0-scene0","l3-low-mixed42-20261012-general_pickup-standard-s0-scene0","l3-low-mixed42-20261012-hang_mugs-random-s0-scene0","l3-low-mixed42-20261012-imitate_sorting_sequence-standard-s0-scene0","l3-low-mixed42-20261012-insert_key-standard-s0-scene0","l3-low-mixed42-20261012-insert_tubes-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-make_kong-standard-s0-scene0","l3-low-mixed42-20261012-make_toast-random-s0-scene0","l3-low-mixed42-20261012-match_and_pick_from_conveyor-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-organize_table-standard-s0-scene0","l3-low-mixed42-20261012-pack_objects_into_box-random-s0-scene0","l3-low-mixed42-20261012-pick_from_conveyor_by_image-standard-s0-scene0","l3-low-mixed42-20261012-play_Xylophone-standard-s0-scene0","l3-low-mixed42-20261012-play_stacking_toy-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-play_tic_tac_toe-standard-s0-scene0","l3-low-mixed42-20261012-plug_in_charger-standard-s0-scene0","l3-low-mixed42-20261012-pour_balls_into_vase-standard-s0-scene0","l3-low-mixed42-20261012-pour_by_language-standard-s0-scene0","l3-low-mixed42-20261012-pour_liquid_into_cup-random-s0-scene0","l3-low-mixed42-20261012-press_by_number-standard-s0-scene0","l3-low-mixed42-20261012-init-retry1-push_T-random-s0-scene0","l3-low-mixed42-20261012-init-repair2-put_bottles_into_dustbin-standard-s0-scene0","l3-low-mixed42-20261012-solve_equation-standard-s0-scene0","l3-low-mixed42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","l3-low-mixed42-20261012-init-repair2-stack_blocks-random-s0-scene0","l3-low-mixed42-20261012-stack_blocks_by_language-standard-s0-scene0","l3_low_stack_bowls_random_s0_scene0_20261012","l3-low-mixed42-20261012-init-video3-store_laptop_and_headphones-random-s0-scene0","l3-low-mixed42-20261012-store_tools_in_toolbox-standard-s0-scene0","l3-low-mixed42-20261012-swap_T-standard-s0-scene0","l3-low-mixed42-20261012-swap_blocks-standard-s0-scene0","l3-low-mixed42-20261012-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-video3-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-fasten_screws-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-imitate_sorting_sequence-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pack_objects_into_box-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-retry1-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_low_stack_bowls_random_s0_scene0_20261012"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-video3-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4583333333333333,"success_rate":0.4583333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.34375,"success_rate":0.1875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.625,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.33125,"success_rate":0.3125},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.03125,"success_rate":0.0}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.35791666666666666,"selected_run_ids":["l3-low-mixed42-20261012-align_blocks-standard-s0-scene0","l3-low-r2-mixed42-20261013-align_blocks-standard-s0-scene1","l3-low-mixed42-20261012-arrange_largest_number-random-s0-scene0","l3-low-r2-mixed42-20261013-arrange_largest_number-standard-s0-scene0","l3-low-mixed42-20261012-init-video3-build_tower-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-classify_objects-standard-s0-scene0","l3-low-r2-mixed42-20261013-classify_objects-standard-s0-scene1","l3-low-mixed42-20261012-classify_objects_by_language-standard-s0-scene0","l3-low-r2-mixed42-20261013-classify_objects_by_language-standard-s0-scene1","l3-low-mixed42-20261012-cover_blocks-standard-s0-scene0","l3-low-r2-mixed42-20261013-cover_blocks-standard-s0-scene1","l3-low-mixed42-20261012-deposit_coin-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-fasten_screws-standard-s0-scene0","l3-low-r2-mixed42-20261013-fasten_screws-standard-s0-scene1","l3-low-mixed42-20261012-init-repair2-fill_egg_holder-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-fill_pen_holder-standard-s0-scene0","l3-low-mixed42-20261012-fold_clothes-random-s0-scene0","l3-low-r2-mixed42-20261013-fold_clothes-standard-s0-scene0","l3-low-mixed42-20261012-general_pickup-standard-s0-scene0","l3-low-r2-mixed42-20261013-general_pickup-standard-s0-scene1","l3-low-mixed42-20261012-hang_mugs-random-s0-scene0","l3-low-mixed42-20261012-imitate_sorting_sequence-standard-s0-scene0","l3-low-r2-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene1","l3-low-mixed42-20261012-insert_key-standard-s0-scene0","l3-low-mixed42-20261012-insert_tubes-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-make_kong-standard-s0-scene0","l3-low-mixed42-20261012-make_toast-random-s0-scene0","l3-low-mixed42-20261012-match_and_pick_from_conveyor-standard-s0-scene0","l3-low-r2-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene1","l3-low-mixed42-20261012-init-repair2-organize_table-standard-s0-scene0","l3-low-mixed42-20261012-pack_objects_into_box-random-s0-scene0","l3-low-r2-mixed42-20261013-pack_objects_into_box-standard-s0-scene0","l3-low-mixed42-20261012-pick_from_conveyor_by_image-standard-s0-scene0","l3-low-r2-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene1","l3-low-mixed42-20261012-play_Xylophone-standard-s0-scene0","l3-low-r2-mixed42-20261013-play_Xylophone-standard-s0-scene1","l3-low-mixed42-20261012-play_stacking_toy-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-play_tic_tac_toe-standard-s0-scene0","l3-low-mixed42-20261012-plug_in_charger-standard-s0-scene0","l3-low-r2-mixed42-20261013-plug_in_charger-standard-s0-scene1","l3-low-mixed42-20261012-pour_balls_into_vase-standard-s0-scene0","l3-low-r2-mixed42-20261013-pour_balls_into_vase-standard-s0-scene1","l3-low-mixed42-20261012-pour_by_language-standard-s0-scene0","l3-low-mixed42-20261012-pour_liquid_into_cup-random-s0-scene0","l3-low-mixed42-20261012-press_by_number-standard-s0-scene0","l3-low-r2-mixed42-20261013-press_by_number-standard-s0-scene1","l3-low-mixed42-20261012-init-retry1-push_T-random-s0-scene0","l3-low-r2-mixed42-20261013-push_T-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-put_bottles_into_dustbin-standard-s0-scene0","l3-low-r2-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene1","l3-low-mixed42-20261012-solve_equation-standard-s0-scene0","l3-low-r2-mixed42-20261013-solve_equation-standard-s0-scene1","l3-low-mixed42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","l3-low-r2-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene0","l3-low-mixed42-20261012-init-repair2-stack_blocks-random-s0-scene0","l3-low-mixed42-20261012-stack_blocks_by_language-standard-s0-scene0","l3-low-r2-mixed42-20261013-stack_blocks_by_language-standard-s0-scene1","l3_low_stack_bowls_random_s0_scene0_20261012","l3-low-r2-mixed42-20261013-stack_bowls-standard-s0-scene0","l3-low-mixed42-20261012-init-video3-store_laptop_and_headphones-random-s0-scene0","l3-low-mixed42-20261012-store_tools_in_toolbox-standard-s0-scene0","l3-low-mixed42-20261012-swap_T-standard-s0-scene0","l3-low-r2-mixed42-20261013-swap_T-standard-s0-scene1","l3-low-mixed42-20261012-swap_blocks-standard-s0-scene0","l3-low-mixed42-20261012-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.30833333333333335,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-align_blocks-standard-s0-scene0","l3-low-r2-mixed42-20261013-align_blocks-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-arrange_largest_number-random-s0-scene0","l3-low-r2-mixed42-20261013-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-video3-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-init-repair2-classify_objects-standard-s0-scene0","l3-low-r2-mixed42-20261013-classify_objects-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-classify_objects_by_language-standard-s0-scene0","l3-low-r2-mixed42-20261013-classify_objects_by_language-standard-s0-scene1"],"score":0.55,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-cover_blocks-standard-s0-scene0","l3-low-r2-mixed42-20261013-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-init-repair2-fasten_screws-standard-s0-scene0","l3-low-r2-mixed42-20261013-fasten_screws-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-fold_clothes-random-s0-scene0","l3-low-r2-mixed42-20261013-fold_clothes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-general_pickup-standard-s0-scene0","l3-low-r2-mixed42-20261013-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-imitate_sorting_sequence-standard-s0-scene0","l3-low-r2-mixed42-20261013-imitate_sorting_sequence-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-match_and_pick_from_conveyor-standard-s0-scene0","l3-low-r2-mixed42-20261013-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-pack_objects_into_box-random-s0-scene0","l3-low-r2-mixed42-20261013-pack_objects_into_box-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-pick_from_conveyor_by_image-standard-s0-scene0","l3-low-r2-mixed42-20261013-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-play_Xylophone-standard-s0-scene0","l3-low-r2-mixed42-20261013-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-plug_in_charger-standard-s0-scene0","l3-low-r2-mixed42-20261013-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-pour_balls_into_vase-standard-s0-scene0","l3-low-r2-mixed42-20261013-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-press_by_number-standard-s0-scene0","l3-low-r2-mixed42-20261013-press_by_number-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-init-retry1-push_T-random-s0-scene0","l3-low-r2-mixed42-20261013-push_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-init-repair2-put_bottles_into_dustbin-standard-s0-scene0","l3-low-r2-mixed42-20261013-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-solve_equation-standard-s0-scene0","l3-low-r2-mixed42-20261013-solve_equation-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","l3-low-r2-mixed42-20261013-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-repair2-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-stack_blocks_by_language-standard-s0-scene0","l3-low-r2-mixed42-20261013-stack_blocks_by_language-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3_low_stack_bowls_random_s0_scene0_20261012","l3-low-r2-mixed42-20261013-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-init-video3-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3-low-mixed42-20261012-swap_T-standard-s0-scene0","l3-low-r2-mixed42-20261013-swap_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3-low-mixed42-20261012-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"2a365f9ad111db2340e31a285e423e2c7d18ae9185b49ea614deff42ba67d192","name":"persistent-cap20 low: eight explicit variant-local scene rounds","selection_id":"low-cap20-rounds8-infra-v2"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":1,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["luna-medium-cap20-smoke-20261016-a4-stack_bowls-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["luna-medium-cap20-smoke-20261016-a4-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":1,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":1,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["luna-medium-cap20-smoke-20261016-a4-stack_bowls-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["luna-medium-cap20-smoke-20261016-a4-stack_bowls-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":1,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["luna-medium-cap20-smoke-20261016-a4-stack_bowls-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["luna-medium-cap20-smoke-20261016-a4-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"fbc192fd4fccb5278cfcdc526052b9a21a301a830834ec8bc79e446092ee1894","name":"luna-medium-cap20-smoke-20261016","selection_id":"luna-medium-cap20-smoke-20261016"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.425,"success_rate":0.375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.246875,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.49583333333333335,"success_rate":0.4583333333333333},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.48125,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.25,"success_rate":0.15625}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.37979166666666664,"selected_run_ids":["l3_persistent_cap20_align_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_align_blocks_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_align_blocks_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_align_blocks_s0_layout3_20261008_v1","l3_persistent_cap20_arrange_largest_number_random_s0_layout0_20261006_v1","l3_persistent_cap20_arrange_largest_number_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_arrange_largest_number_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_arrange_largest_number_s0_layout1_20261008_v1","l3_persistent_cap20_build_tower_s0_layout0_20261006_v1","l3_persistent_cap20_classify_objects_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_classify_objects_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_classify_objects_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_classify_objects_s0_layout3_20261008_v1","l3_persistent_cap20_classify_objects_by_language_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout3_20261008_v1","l3_persistent_cap20_cover_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_cover_blocks_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_cover_blocks_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_cover_blocks_s0_layout3_20261008_v1","l3_persistent_cap20_deposit_coin_s0_layout0_20261006_v1","l3_persistent_cap20_fasten_screws_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_fasten_screws_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_fasten_screws_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_fasten_screws_s0_layout3_20261008_v1","l3_persistent_cap20_fill_egg_holder_s0_layout0_20261006_v1","l3_persistent_cap20_fill_pen_holder_s0_layout0_20261006_v1","l3_persistent_cap20_fold_clothes_random_s0_layout0_20261006_v1","l3_persistent_cap20_fold_clothes_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_fold_clothes_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_fold_clothes_s0_layout1_20261008_v1","l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","l3_persistent_cap20_repeat_general_pickup_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_general_pickup_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_general_pickup_s0_layout3_20261008_v1","l3_persistent_cap20_hang_mugs_random_s0_layout0_20261006_v1","l3_persistent_cap20_imitate_sorting_sequence_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout3_20261008_v1","l3_persistent_cap20_insert_key_s0_layout0_20261006_v1","l3_persistent_cap20_insert_tubes_s0_layout0_20261006_v1","l3_persistent_cap20_make_kong_s0_layout0_20261006_v1","l3_persistent_cap20_make_toast_random_s0_layout0_20261006_v1","l3_persistent_cap20_match_and_pick_from_conveyor_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout3_20261008_v1","l3_persistent_cap20_organize_table_s0_layout0_20261006_v1","l3_persistent_cap20_pack_objects_into_box_random_s0_layout0_20261006_v1","l3_persistent_cap20_pack_objects_into_box_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pack_objects_into_box_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_pack_objects_into_box_s0_layout1_20261008_v1","l3_persistent_cap20_pick_from_conveyor_by_image_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout3_20261008_v1","l3_persistent_cap20_play_Xylophone_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_play_Xylophone_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_play_Xylophone_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_play_Xylophone_s0_layout3_20261008_v1","l3_persistent_cap20_play_stacking_toy_s0_layout0_20261006_v1","l3_persistent_cap20_play_tic_tac_toe_s0_layout0_20261006_v1","l3_persistent_cap20_plug_in_charger_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_plug_in_charger_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_plug_in_charger_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_plug_in_charger_s0_layout3_20261008_v1","l3_persistent_cap20_pour_balls_into_vase_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout3_20261008_v1","l3_persistent_cap20_pour_by_language_s0_layout0_20261006_v1","l3_persistent_cap20_pour_liquid_into_cup_random_s0_layout0_20261006_v1","l3_persistent_cap20_press_by_number_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_press_by_number_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_press_by_number_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_press_by_number_s0_layout3_20261008_v1","l3_persistent_cap20_push_T_random_s0_layout0_20261006_v1","l3_persistent_cap20_push_T_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_push_T_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_push_T_s0_layout1_20261008_v1","l3_persistent_cap20_put_bottles_into_dustbin_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout3_20261008_v1","l3_persistent_cap20_solve_equation_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_solve_equation_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_solve_equation_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_solve_equation_s0_layout3_20261008_v1","l3_persistent_cap20_sort_nesting_dolls_by_size_random_s0_layout0_20261006_v1","l3_persistent_cap20_sort_nesting_dolls_by_size_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_sort_nesting_dolls_by_size_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_sort_nesting_dolls_by_size_s0_layout1_20261008_v1","l3_persistent_cap20_stack_blocks_random_s0_layout0_20261006_v1","l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout3_20261008_v1","l3_persistent_cap20_stack_bowls_random_s0_layout0_20261006_v1","l3_persistent_cap20_stack_bowls_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_stack_bowls_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_stack_bowls_s0_layout1_20261008_v1","l3_persistent_cap20_store_laptop_and_headphones_random_s0_layout0_20261006_v1","l3_persistent_cap20_store_tools_in_toolbox_s0_layout0_20261006_v1","l3_persistent_cap20_swap_T_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_swap_T_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_swap_T_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_swap_T_s0_layout3_20261008_v1","l3_persistent_cap20_swap_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_sweep_blocks_random_s0_layout0_20261006_v1"],"status":"complete","success_rate":0.3104166666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_align_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_align_blocks_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_align_blocks_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_align_blocks_s0_layout3_20261008_v1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_arrange_largest_number_random_s0_layout0_20261006_v1","l3_persistent_cap20_arrange_largest_number_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_arrange_largest_number_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_arrange_largest_number_s0_layout1_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_build_tower_s0_layout0_20261006_v1"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_classify_objects_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_classify_objects_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_classify_objects_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_classify_objects_s0_layout3_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_classify_objects_by_language_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout3_20261008_v1"],"score":0.55,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_cover_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_cover_blocks_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_cover_blocks_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_cover_blocks_s0_layout3_20261008_v1"],"score":0.325,"success_rate":0.25,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_deposit_coin_s0_layout0_20261006_v1"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_fasten_screws_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_fasten_screws_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_fasten_screws_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_fasten_screws_s0_layout3_20261008_v1"],"score":0.6,"success_rate":0.5,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_fill_egg_holder_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_fill_pen_holder_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_fold_clothes_random_s0_layout0_20261006_v1","l3_persistent_cap20_fold_clothes_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_fold_clothes_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_fold_clothes_s0_layout1_20261008_v1"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","l3_persistent_cap20_repeat_general_pickup_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_general_pickup_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_general_pickup_s0_layout3_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_hang_mugs_random_s0_layout0_20261006_v1"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_imitate_sorting_sequence_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout3_20261008_v1"],"score":0.65,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_insert_key_s0_layout0_20261006_v1"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_insert_tubes_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_make_kong_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_make_toast_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_match_and_pick_from_conveyor_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout3_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_organize_table_s0_layout0_20261006_v1"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_pack_objects_into_box_random_s0_layout0_20261006_v1","l3_persistent_cap20_pack_objects_into_box_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pack_objects_into_box_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_pack_objects_into_box_s0_layout1_20261008_v1"],"score":0.1125,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_pick_from_conveyor_by_image_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout3_20261008_v1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_play_Xylophone_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_play_Xylophone_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_play_Xylophone_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_play_Xylophone_s0_layout3_20261008_v1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_play_stacking_toy_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_play_tic_tac_toe_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_plug_in_charger_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_plug_in_charger_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_plug_in_charger_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_plug_in_charger_s0_layout3_20261008_v1"],"score":0.75,"success_rate":0.75,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_pour_balls_into_vase_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout3_20261008_v1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pour_by_language_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pour_liquid_into_cup_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_press_by_number_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_press_by_number_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_press_by_number_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_press_by_number_s0_layout3_20261008_v1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_push_T_random_s0_layout0_20261006_v1","l3_persistent_cap20_push_T_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_push_T_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_push_T_s0_layout1_20261008_v1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_put_bottles_into_dustbin_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout3_20261008_v1"],"score":0.325,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_solve_equation_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_solve_equation_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_solve_equation_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_solve_equation_s0_layout3_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_sort_nesting_dolls_by_size_random_s0_layout0_20261006_v1","l3_persistent_cap20_sort_nesting_dolls_by_size_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_sort_nesting_dolls_by_size_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_sort_nesting_dolls_by_size_s0_layout1_20261008_v1"],"score":0.75,"success_rate":0.75,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_stack_blocks_random_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout3_20261008_v1"],"score":0.8,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_stack_bowls_random_s0_layout0_20261006_v1","l3_persistent_cap20_stack_bowls_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_stack_bowls_random_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_stack_bowls_s0_layout1_20261008_v1"],"score":0.7875,"success_rate":0.75,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_store_laptop_and_headphones_random_s0_layout0_20261006_v1"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_store_tools_in_toolbox_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["l3_persistent_cap20_swap_T_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_swap_T_s0_layout1_20261008_v1","l3_persistent_cap20_repeat_swap_T_s0_layout2_20261008_v1","l3_persistent_cap20_repeat_swap_T_s0_layout3_20261008_v1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_swap_blocks_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_sweep_blocks_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.48333333333333334,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.25625,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.525,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.625,"success_rate":0.625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.23125,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.4241666666666667,"selected_run_ids":["l3_persistent_cap20_align_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_arrange_largest_number_random_s0_layout0_20261006_v1","l3_persistent_cap20_build_tower_s0_layout0_20261006_v1","l3_persistent_cap20_classify_objects_s0_layout0_20261006_v1","l3_persistent_cap20_classify_objects_by_language_s0_layout0_20261006_v1","l3_persistent_cap20_cover_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_deposit_coin_s0_layout0_20261006_v1","l3_persistent_cap20_fasten_screws_s0_layout0_20261006_v1","l3_persistent_cap20_fill_egg_holder_s0_layout0_20261006_v1","l3_persistent_cap20_fill_pen_holder_s0_layout0_20261006_v1","l3_persistent_cap20_fold_clothes_random_s0_layout0_20261006_v1","l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","l3_persistent_cap20_hang_mugs_random_s0_layout0_20261006_v1","l3_persistent_cap20_imitate_sorting_sequence_s0_layout0_20261006_v1","l3_persistent_cap20_insert_key_s0_layout0_20261006_v1","l3_persistent_cap20_insert_tubes_s0_layout0_20261006_v1","l3_persistent_cap20_make_kong_s0_layout0_20261006_v1","l3_persistent_cap20_make_toast_random_s0_layout0_20261006_v1","l3_persistent_cap20_match_and_pick_from_conveyor_s0_layout0_20261006_v1","l3_persistent_cap20_organize_table_s0_layout0_20261006_v1","l3_persistent_cap20_pack_objects_into_box_random_s0_layout0_20261006_v1","l3_persistent_cap20_pick_from_conveyor_by_image_s0_layout0_20261006_v1","l3_persistent_cap20_play_Xylophone_s0_layout0_20261006_v1","l3_persistent_cap20_play_stacking_toy_s0_layout0_20261006_v1","l3_persistent_cap20_play_tic_tac_toe_s0_layout0_20261006_v1","l3_persistent_cap20_plug_in_charger_s0_layout0_20261006_v1","l3_persistent_cap20_pour_balls_into_vase_s0_layout0_20261006_v1","l3_persistent_cap20_pour_by_language_s0_layout0_20261006_v1","l3_persistent_cap20_pour_liquid_into_cup_random_s0_layout0_20261006_v1","l3_persistent_cap20_press_by_number_s0_layout0_20261006_v1","l3_persistent_cap20_push_T_random_s0_layout0_20261006_v1","l3_persistent_cap20_put_bottles_into_dustbin_s0_layout0_20261006_v1","l3_persistent_cap20_solve_equation_s0_layout0_20261006_v1","l3_persistent_cap20_sort_nesting_dolls_by_size_random_s0_layout0_20261006_v1","l3_persistent_cap20_stack_blocks_random_s0_layout0_20261006_v1","l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","l3_persistent_cap20_stack_bowls_random_s0_layout0_20261006_v1","l3_persistent_cap20_store_laptop_and_headphones_random_s0_layout0_20261006_v1","l3_persistent_cap20_store_tools_in_toolbox_s0_layout0_20261006_v1","l3_persistent_cap20_swap_T_s0_layout0_20261006_v1","l3_persistent_cap20_swap_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_sweep_blocks_random_s0_layout0_20261006_v1"],"status":"complete","success_rate":0.35833333333333334,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_align_blocks_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_arrange_largest_number_random_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_build_tower_s0_layout0_20261006_v1"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_classify_objects_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_classify_objects_by_language_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_cover_blocks_s0_layout0_20261006_v1"],"score":0.15,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_deposit_coin_s0_layout0_20261006_v1"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_fasten_screws_s0_layout0_20261006_v1"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_fill_egg_holder_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_fill_pen_holder_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_fold_clothes_random_s0_layout0_20261006_v1"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_v1_general_pickup_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_hang_mugs_random_s0_layout0_20261006_v1"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_imitate_sorting_sequence_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_insert_key_s0_layout0_20261006_v1"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_insert_tubes_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_make_kong_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_make_toast_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_match_and_pick_from_conveyor_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_organize_table_s0_layout0_20261006_v1"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pack_objects_into_box_random_s0_layout0_20261006_v1"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pick_from_conveyor_by_image_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_play_Xylophone_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_play_stacking_toy_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_play_tic_tac_toe_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_plug_in_charger_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pour_balls_into_vase_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pour_by_language_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pour_liquid_into_cup_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_press_by_number_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_push_T_random_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_put_bottles_into_dustbin_s0_layout0_20261006_v1"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_solve_equation_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_sort_nesting_dolls_by_size_random_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_stack_blocks_random_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_stack_bowls_random_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_store_laptop_and_headphones_random_s0_layout0_20261006_v1"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_store_tools_in_toolbox_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_swap_T_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_swap_blocks_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_sweep_blocks_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.46875,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2375,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.45416666666666666,"success_rate":0.4166666666666667},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.5875,"success_rate":0.5625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.23125,"success_rate":0.125}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.39583333333333337,"selected_run_ids":["l3_persistent_cap20_align_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_align_blocks_s0_layout1_20261008_v1","l3_persistent_cap20_arrange_largest_number_random_s0_layout0_20261006_v1","l3_persistent_cap20_arrange_largest_number_s0_layout0_20261006_v1","l3_persistent_cap20_build_tower_s0_layout0_20261006_v1","l3_persistent_cap20_classify_objects_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_classify_objects_s0_layout1_20261008_v1","l3_persistent_cap20_classify_objects_by_language_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout1_20261008_v1","l3_persistent_cap20_cover_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_cover_blocks_s0_layout1_20261008_v1","l3_persistent_cap20_deposit_coin_s0_layout0_20261006_v1","l3_persistent_cap20_fasten_screws_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_fasten_screws_s0_layout1_20261008_v1","l3_persistent_cap20_fill_egg_holder_s0_layout0_20261006_v1","l3_persistent_cap20_fill_pen_holder_s0_layout0_20261006_v1","l3_persistent_cap20_fold_clothes_random_s0_layout0_20261006_v1","l3_persistent_cap20_fold_clothes_s0_layout0_20261006_v1","l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","l3_persistent_cap20_repeat_general_pickup_s0_layout1_20261008_v1","l3_persistent_cap20_hang_mugs_random_s0_layout0_20261006_v1","l3_persistent_cap20_imitate_sorting_sequence_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout1_20261008_v1","l3_persistent_cap20_insert_key_s0_layout0_20261006_v1","l3_persistent_cap20_insert_tubes_s0_layout0_20261006_v1","l3_persistent_cap20_make_kong_s0_layout0_20261006_v1","l3_persistent_cap20_make_toast_random_s0_layout0_20261006_v1","l3_persistent_cap20_match_and_pick_from_conveyor_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout1_20261008_v1","l3_persistent_cap20_organize_table_s0_layout0_20261006_v1","l3_persistent_cap20_pack_objects_into_box_random_s0_layout0_20261006_v1","l3_persistent_cap20_pack_objects_into_box_s0_layout0_20261006_v1","l3_persistent_cap20_pick_from_conveyor_by_image_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout1_20261008_v1","l3_persistent_cap20_play_Xylophone_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_play_Xylophone_s0_layout1_20261008_v1","l3_persistent_cap20_play_stacking_toy_s0_layout0_20261006_v1","l3_persistent_cap20_play_tic_tac_toe_s0_layout0_20261006_v1","l3_persistent_cap20_plug_in_charger_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_plug_in_charger_s0_layout1_20261008_v1","l3_persistent_cap20_pour_balls_into_vase_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout1_20261008_v1","l3_persistent_cap20_pour_by_language_s0_layout0_20261006_v1","l3_persistent_cap20_pour_liquid_into_cup_random_s0_layout0_20261006_v1","l3_persistent_cap20_press_by_number_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_press_by_number_s0_layout1_20261008_v1","l3_persistent_cap20_push_T_random_s0_layout0_20261006_v1","l3_persistent_cap20_push_T_s0_layout0_20261006_v1","l3_persistent_cap20_put_bottles_into_dustbin_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout1_20261008_v1","l3_persistent_cap20_solve_equation_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_solve_equation_s0_layout1_20261008_v1","l3_persistent_cap20_sort_nesting_dolls_by_size_random_s0_layout0_20261006_v1","l3_persistent_cap20_sort_nesting_dolls_by_size_s0_layout0_20261006_v1","l3_persistent_cap20_stack_blocks_random_s0_layout0_20261006_v1","l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout1_20261008_v1","l3_persistent_cap20_stack_bowls_random_s0_layout0_20261006_v1","l3_persistent_cap20_stack_bowls_s0_layout0_20261006_v1","l3_persistent_cap20_store_laptop_and_headphones_random_s0_layout0_20261006_v1","l3_persistent_cap20_store_tools_in_toolbox_s0_layout0_20261006_v1","l3_persistent_cap20_swap_T_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_swap_T_s0_layout1_20261008_v1","l3_persistent_cap20_swap_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_sweep_blocks_random_s0_layout0_20261006_v1"],"status":"complete","success_rate":0.3291666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_align_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_align_blocks_s0_layout1_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_arrange_largest_number_random_s0_layout0_20261006_v1","l3_persistent_cap20_arrange_largest_number_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_build_tower_s0_layout0_20261006_v1"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_classify_objects_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_classify_objects_s0_layout1_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_classify_objects_by_language_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_classify_objects_by_language_s0_layout1_20261008_v1"],"score":0.7,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_cover_blocks_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_cover_blocks_s0_layout1_20261008_v1"],"score":0.575,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_deposit_coin_s0_layout0_20261006_v1"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_fasten_screws_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_fasten_screws_s0_layout1_20261008_v1"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_fill_egg_holder_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_fill_pen_holder_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_fold_clothes_random_s0_layout0_20261006_v1","l3_persistent_cap20_fold_clothes_s0_layout0_20261006_v1"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","l3_persistent_cap20_repeat_general_pickup_s0_layout1_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_hang_mugs_random_s0_layout0_20261006_v1"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_imitate_sorting_sequence_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_imitate_sorting_sequence_s0_layout1_20261008_v1"],"score":0.65,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_insert_key_s0_layout0_20261006_v1"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_insert_tubes_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_make_kong_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_make_toast_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_match_and_pick_from_conveyor_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_match_and_pick_from_conveyor_s0_layout1_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_organize_table_s0_layout0_20261006_v1"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_pack_objects_into_box_random_s0_layout0_20261006_v1","l3_persistent_cap20_pack_objects_into_box_s0_layout0_20261006_v1"],"score":0.175,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_pick_from_conveyor_by_image_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pick_from_conveyor_by_image_s0_layout1_20261008_v1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_play_Xylophone_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_play_Xylophone_s0_layout1_20261008_v1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_play_stacking_toy_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_play_tic_tac_toe_s0_layout0_20261006_v1"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_plug_in_charger_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_plug_in_charger_s0_layout1_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_pour_balls_into_vase_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_pour_balls_into_vase_s0_layout1_20261008_v1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pour_by_language_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_pour_liquid_into_cup_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_press_by_number_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_press_by_number_s0_layout1_20261008_v1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_push_T_random_s0_layout0_20261006_v1","l3_persistent_cap20_push_T_s0_layout0_20261006_v1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_put_bottles_into_dustbin_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_put_bottles_into_dustbin_s0_layout1_20261008_v1"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_solve_equation_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_solve_equation_s0_layout1_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_sort_nesting_dolls_by_size_random_s0_layout0_20261006_v1","l3_persistent_cap20_sort_nesting_dolls_by_size_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_stack_blocks_random_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","l3_persistent_cap20_repeat_stack_blocks_by_language_s0_layout1_20261008_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_stack_bowls_random_s0_layout0_20261006_v1","l3_persistent_cap20_stack_bowls_s0_layout0_20261006_v1"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_store_laptop_and_headphones_random_s0_layout0_20261006_v1"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_store_tools_in_toolbox_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["l3_persistent_cap20_swap_T_s0_layout0_20261006_v1","l3_persistent_cap20_repeat_swap_T_s0_layout1_20261008_v1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_swap_blocks_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["l3_persistent_cap20_sweep_blocks_random_s0_layout0_20261006_v1"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"27b842299e63b01aec72e4050550bc8b4102412d13c78be704464e53ad8f5fee","name":"persistent-cap20","selection_id":"medium-cap20-rounds4-v2"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["o23-coding-gt-round1-restart-20261103-154255-align_blocks-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-arrange_largest_number-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-build_tower-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-classify_objects-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-classify_objects_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-cover_blocks-standard-s0-scene0","o23-coding-precision4-20261102-135343-coinfix2-deposit_coin-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fasten_screws-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fill_egg_holder-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fill_pen_holder-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fold_clothes-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-general_pickup-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-hang_mugs-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-imitate_sorting_sequence-standard-s0-scene0","o23-coding-precision4-20261102-135343-insert_key-standard-s0-scene0","o23-coding-precision4-20261102-135343-insert_tubes-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-make_kong-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-make_toast-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-match_and_pick_from_conveyor-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-organize_table-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pack_objects_into_box-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pick_from_conveyor_by_image-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_Xylophone-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_stacking_toy-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_tic_tac_toe-standard-s0-scene0","o23-coding-precision4-20261102-135343-plug_in_charger-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_balls_into_vase-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_liquid_into_cup-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-press_by_number-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-push_T-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-put_bottles_into_dustbin-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-solve_equation-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-sort_nesting_dolls_by_size-random-s0-scene0","o23-coding-depth-pilot-20261102-131035-stack_blocks-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-stack_blocks_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-stack_bowls-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-store_laptop_and_headphones-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-store_tools_in_toolbox-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-swap_T-standard-s0-scene0","o23-coding-gt-swap-restart-20261103-230600-swap_blocks-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-coinfix2-deposit_coin-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_tic_tac_toe-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-coding-precision4-20261102-135343-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-depth-pilot-20261102-131035-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-coding-gt-swap-restart-20261103-230600-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.39166666666666666,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.33125,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.58125,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.38125,"success_rate":0.25}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.4370833333333334,"selected_run_ids":["o23-coding-gt-round1-restart-20261103-154255-align_blocks-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-arrange_largest_number-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-build_tower-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-classify_objects-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-classify_objects_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-cover_blocks-standard-s0-scene0","o23-coding-precision4-20261102-135343-coinfix2-deposit_coin-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fasten_screws-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fill_egg_holder-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fill_pen_holder-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fold_clothes-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-general_pickup-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-hang_mugs-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-imitate_sorting_sequence-standard-s0-scene0","o23-coding-precision4-20261102-135343-insert_key-standard-s0-scene0","o23-coding-precision4-20261102-135343-insert_tubes-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-make_kong-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-make_toast-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-match_and_pick_from_conveyor-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-organize_table-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pack_objects_into_box-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pick_from_conveyor_by_image-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_Xylophone-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_stacking_toy-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_tic_tac_toe-standard-s0-scene0","o23-coding-precision4-20261102-135343-plug_in_charger-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_balls_into_vase-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_liquid_into_cup-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-press_by_number-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-push_T-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-put_bottles_into_dustbin-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-solve_equation-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-sort_nesting_dolls_by_size-random-s0-scene0","o23-coding-depth-pilot-20261102-131035-stack_blocks-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-stack_blocks_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-stack_bowls-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-store_laptop_and_headphones-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-store_tools_in_toolbox-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-swap_T-standard-s0-scene0","o23-coding-gt-swap-restart-20261103-230600-swap_blocks-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3416666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-arrange_largest_number-random-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-coinfix2-deposit_coin-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-imitate_sorting_sequence-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pack_objects_into_box-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_tic_tac_toe-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-plug_in_charger-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-depth-pilot-20261102-131035-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-coding-gt-swap-restart-20261103-230600-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["o23-coding-gt-round1-restart-20261103-154255-align_blocks-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-arrange_largest_number-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-build_tower-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-classify_objects-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-classify_objects_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-cover_blocks-standard-s0-scene0","o23-coding-precision4-20261102-135343-coinfix2-deposit_coin-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fasten_screws-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fill_egg_holder-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fill_pen_holder-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-fold_clothes-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-general_pickup-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-hang_mugs-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-imitate_sorting_sequence-standard-s0-scene0","o23-coding-precision4-20261102-135343-insert_key-standard-s0-scene0","o23-coding-precision4-20261102-135343-insert_tubes-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-make_kong-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-make_toast-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-match_and_pick_from_conveyor-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-organize_table-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pack_objects_into_box-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pick_from_conveyor_by_image-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_Xylophone-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_stacking_toy-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-play_tic_tac_toe-standard-s0-scene0","o23-coding-precision4-20261102-135343-plug_in_charger-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_balls_into_vase-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-pour_liquid_into_cup-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-press_by_number-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-push_T-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-put_bottles_into_dustbin-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-solve_equation-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-sort_nesting_dolls_by_size-random-s0-scene0","o23-coding-depth-pilot-20261102-131035-stack_blocks-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-stack_blocks_by_language-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-stack_bowls-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-store_laptop_and_headphones-random-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-store_tools_in_toolbox-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-swap_T-standard-s0-scene0","o23-coding-gt-swap-restart-20261103-230600-swap_blocks-standard-s0-scene0","o23-coding-gt-round1-restart-20261103-154255-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-coinfix2-deposit_coin-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-coding-precision4-20261102-135343-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-play_tic_tac_toe-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-coding-precision4-20261102-135343-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-depth-pilot-20261102-131035-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-coding-gt-swap-restart-20261103-230600-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-coding-gt-round1-restart-20261103-154255-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"f8b8c5ce4101d822671d40511b13846627194044319f088304e39dc6a930302e","name":"O23-GT + Coding · 100决策 · 首轮42","selection_id":"o23-coding-gt-mixed42-round1-20261104"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.47291666666666665,"success_rate":0.4375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.521875,"success_rate":0.375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.7083333333333334,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.521875,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.290625,"success_rate":0.1875}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.503125,"selected_run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-arrange_largest_number-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-arrange_largest_number-random-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-arrange_largest_number-standard-s0-scene1","o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-classify_objects_by_language-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects_by_language-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects_by_language-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene3","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-fold_clothes-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fold_clothes-random-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fold_clothes-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene3","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-imitate_sorting_sequence-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-imitate_sorting_sequence-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-imitate_sorting_sequence-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-random-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-pack_objects_into_box-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-play_Xylophone-standard-s0-scene3","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-plug_in_charger-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-press_by_number-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-press_by_number-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-press_by_number-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-push_T-random-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sort_nesting_dolls_by_size-random-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-random-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-stack_bowls-standard-s0-scene1","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-swap_T-standard-s0-scene3","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.4333333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-arrange_largest_number-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-arrange_largest_number-random-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-arrange_largest_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene3"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-classify_objects_by_language-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects_by_language-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects_by_language-standard-s0-scene3"],"score":0.375,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene3"],"score":0.175,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-fold_clothes-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fold_clothes-random-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fold_clothes-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-imitate_sorting_sequence-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-imitate_sorting_sequence-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-imitate_sorting_sequence-standard-s0-scene3"],"score":0.75,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-random-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-pack_objects_into_box-standard-s0-scene1"],"score":0.6875,"success_rate":0.5,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-plug_in_charger-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-press_by_number-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-press_by_number-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-press_by_number-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-push_T-random-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.625,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sort_nesting_dolls_by_size-random-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene2","o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene3"],"score":0.8,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-random-s0-scene1","o23-depthpro-coding-unlimited-dev39-rerun-20261104-stack_bowls-standard-s0-scene1"],"score":0.7875,"success_rate":0.75,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene1","o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene2","o23-depthpro-coding-unlimited-dev39-rerun-20261104-swap_T-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.45416666666666666,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.5125,"success_rate":0.375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.75,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.625,"success_rate":0.625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.35625,"success_rate":0.25}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.5395833333333333,"selected_run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.4666666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.48541666666666666,"success_rate":0.4583333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.521875,"success_rate":0.375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.7083333333333334,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.51875,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.28125,"success_rate":0.1875}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.503125,"selected_run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-arrange_largest_number-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-classify_objects_by_language-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene1","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-fold_clothes-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene1","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-imitate_sorting_sequence-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene1","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-press_by_number-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene1","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.4375,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-align_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-classify_objects-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-classify_objects_by_language-standard-s0-scene1"],"score":0.55,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-fasten_screws-standard-s0-scene1"],"score":0.1,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-fold_clothes-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-imitate_sorting_sequence-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pack_objects_into_box-standard-s0-scene0"],"score":0.625,"success_rate":0.5,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-sim51-replacement1-plug_in_charger-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-push_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.625,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","o23-depthpro-coding-unlimited-dev39-rerun-20261104-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_blocks_by_language-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","o23-depthpro-coding-unlimited-dev69-20261102-swap_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"7f25b1b6d2c5f5ee6e80bbc37910a5274a4ad399664bace4e324328b56728f48","name":"O23-DepthPro + Coding · Devset","selection_id":"o23-depthpro-coding-unlimited-devset-111"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":3,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null}},"completed":8,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":3,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null}},"completed":8,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":3,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null}},"completed":8,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"922e4222862aa627158a46d8089872a9aab832d78ffc645ebf53e6e4d61780bb","name":"o23-depthpro · coding · 无决策轮次上限 · 8项","selection_id":"o23-depthpro-coding-unlimited-eight-20261030"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.45416666666666666,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.5125,"success_rate":0.375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.75,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.625,"success_rate":0.625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.35625,"success_rate":0.25}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.5395833333333333,"selected_run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.4666666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0","o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0","o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-insert_tubes-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-organize_table-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-play_stacking_toy-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-play_tic_tac_toe-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-eight-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-first42-add34-20261030-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"f491af77916615632067bbb1fe5a44e934cdfdd043d434afffb1ac44be9aa0d8","name":"O23-DepthPro + Coding · 首轮42","selection_id":"o23-depthpro-coding-unlimited-first42-20261030"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":1,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":5,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-pour_liquid_into_cup-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":2,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null}},"completed":5,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-pack_objects_into_box-random-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-pour_liquid_into_cup-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":1,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":5,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-fasten_screws-standard-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-pack_objects_into_box-random-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-play_Xylophone-standard-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-coding-unlimited-fixprompt-20261102-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-pour_liquid_into_cup-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-coding-unlimited-fixprompt-20261102-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"04125cdc21c749943effdd733bed1fecce9d72e3e35a537a921956b3dcea0144","name":"o23-depthpro-coding-unlimited-fixprompt","selection_id":"o23-depthpro-coding-unlimited-fixprompt"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["b2-full-round-20261105-storage-retry1-align_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-arrange_largest_number-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-build_tower-standard-s0-scene0","b2-full-round-20261105-storage-retry1-classify_objects-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-classify_objects_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-cover_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-deposit_coin-standard-s0-scene0","b2-full-round-20261105-initretry1-fasten_screws-standard-s0-scene0","b2-full-round-20261105-initretry1-fill_egg_holder-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fill_pen_holder-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fold_clothes-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-general_pickup-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-hang_mugs-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_key-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_tubes-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_kong-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_toast-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-organize_table-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pack_objects_into_box-random-s0-scene0","b2-full-round-20261105-storage-retry1-initretry1-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_Xylophone-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_stacking_toy-standard-s0-scene0","b2-full-round-20261105-storage-retry1-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-plug_in_charger-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-press_by_number-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-push_T-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-solve_equation-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_blocks-random-s0-scene0","b2-full-round-20261105-storage-retry1-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_bowls-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-store_laptop_and_headphones-random-s0-scene0","b2-full-round-20261105-enospc-retry1-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_T-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["b2-full-round-20261105-storage-retry1-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-build_tower-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["b2-full-round-20261105-storage-retry1-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["b2-full-round-20261105-initretry1-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-initretry1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["b2-full-round-20261105-storage-retry1-initretry1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-storage-retry1-play_tic_tac_toe-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["b2-full-round-20261105-storage-retry1-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-enospc-retry1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4875,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.35625,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5499999999999999,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.625,"success_rate":0.625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.21875,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.44749999999999995,"selected_run_ids":["b2-full-round-20261105-storage-retry1-align_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-arrange_largest_number-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-build_tower-standard-s0-scene0","b2-full-round-20261105-storage-retry1-classify_objects-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-classify_objects_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-cover_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-deposit_coin-standard-s0-scene0","b2-full-round-20261105-initretry1-fasten_screws-standard-s0-scene0","b2-full-round-20261105-initretry1-fill_egg_holder-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fill_pen_holder-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fold_clothes-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-general_pickup-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-hang_mugs-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_key-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_tubes-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_kong-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_toast-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-organize_table-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pack_objects_into_box-random-s0-scene0","b2-full-round-20261105-storage-retry1-initretry1-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_Xylophone-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_stacking_toy-standard-s0-scene0","b2-full-round-20261105-storage-retry1-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-plug_in_charger-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-press_by_number-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-push_T-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-solve_equation-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_blocks-random-s0-scene0","b2-full-round-20261105-storage-retry1-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_bowls-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-store_laptop_and_headphones-random-s0-scene0","b2-full-round-20261105-enospc-retry1-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_T-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.35833333333333334,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-storage-retry1-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-build_tower-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-storage-retry1-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-cover_blocks-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-initretry1-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-initretry1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pack_objects_into_box-random-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-storage-retry1-initretry1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-storage-retry1-play_tic_tac_toe-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-press_by_number-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sort_nesting_dolls_by_size-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-storage-retry1-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-enospc-retry1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["b2-full-round-20261105-storage-retry1-align_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-arrange_largest_number-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-build_tower-standard-s0-scene0","b2-full-round-20261105-storage-retry1-classify_objects-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-classify_objects_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-cover_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-deposit_coin-standard-s0-scene0","b2-full-round-20261105-initretry1-fasten_screws-standard-s0-scene0","b2-full-round-20261105-initretry1-fill_egg_holder-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fill_pen_holder-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fold_clothes-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-general_pickup-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-hang_mugs-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-imitate_sorting_sequence-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_key-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_tubes-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_kong-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_toast-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-match_and_pick_from_conveyor-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-organize_table-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pack_objects_into_box-random-s0-scene0","b2-full-round-20261105-storage-retry1-initretry1-pick_from_conveyor_by_image-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_Xylophone-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_stacking_toy-standard-s0-scene0","b2-full-round-20261105-storage-retry1-play_tic_tac_toe-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-plug_in_charger-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_balls_into_vase-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_liquid_into_cup-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-press_by_number-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-push_T-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-put_bottles_into_dustbin-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-solve_equation-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sort_nesting_dolls_by_size-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_blocks-random-s0-scene0","b2-full-round-20261105-storage-retry1-stack_blocks_by_language-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_bowls-random-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-store_laptop_and_headphones-random-s0-scene0","b2-full-round-20261105-enospc-retry1-store_tools_in_toolbox-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_T-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_blocks-standard-s0-scene0","o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["b2-full-round-20261105-storage-retry1-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-build_tower-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["b2-full-round-20261105-storage-retry1-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["b2-full-round-20261105-initretry1-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-initretry1-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["b2-full-round-20261105-storage-retry1-initretry1-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-storage-retry1-play_tic_tac_toe-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["b2-full-round-20261105-storage-retry1-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["b2-full-round-20261105-enospc-retry1-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23-depthpro-mixed42-s0-scene0-cap20-medium-unlimited-b2-full-round-20261105-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"cdd1c481543103fa5c7a0a77c5b84328b2d7e34fef8fba7abc4c69265e180aa8","name":"O23-DepthPro · 无 Coding · 无决策轮数上限 · 首轮42","selection_id":"o23-depthpro-unlimited"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":3,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null}},"completed":8,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-build_tower-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-fill_egg_holder-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-fill_pen_holder-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-hang_mugs-random-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-insert_tubes-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-make_toast-random-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-play_stacking_toy-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-store_laptop_and_headphones-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":3,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null}},"completed":8,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-build_tower-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-fill_egg_holder-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-fill_pen_holder-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-hang_mugs-random-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-insert_tubes-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-make_toast-random-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-play_stacking_toy-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-store_laptop_and_headphones-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":3,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null}},"completed":8,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-build_tower-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-fill_egg_holder-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-fill_pen_holder-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-hang_mugs-random-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-insert_tubes-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-make_toast-random-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-play_stacking_toy-standard-s0-scene0","o23456-compact-first42-eight-sim-rerun-20261030-store_laptop_and_headphones-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-eight-sim-rerun-20261030-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"1513b51289146e30c4ea48d0a0e7c944a5c3db1d3b29d87ec50f0c3c54a82cc9","name":"o23456-compact · 首轮8项仿真复跑","selection_id":"o23456-compact-first42-eight-sim-rerun-20261030"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.3875,"success_rate":0.3541666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2609375,"success_rate":0.09375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6916666666666668,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.5,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.265625,"success_rate":0.1875}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.4211458333333334,"selected_run_ids":["o23456-compact-first42-20261028-align_blocks-standard-s0-scene0","o23456-compact-dev69-20261029-align_blocks-standard-s0-scene1","o23456-compact-dev69-20261029-align_blocks-standard-s0-scene2","o23456-compact-dev69-20261029-align_blocks-standard-s0-scene3","o23456-compact-first42-20261028-arrange_largest_number-random-s0-scene0","o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene0","o23456-compact-dev69-20261029-arrange_largest_number-random-s0-scene1","o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene1","o23456-compact-first42-20261028-build_tower-standard-s0-scene0","o23456-compact-first42-20261028-classify_objects-standard-s0-scene0","o23456-compact-dev69-20261029-classify_objects-standard-s0-scene1","o23456-compact-dev69-20261029-classify_objects-standard-s0-scene2","o23456-compact-dev69-20261029-classify_objects-standard-s0-scene3","o23456-compact-first42-20261028-classify_objects_by_language-standard-s0-scene0","o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene1","o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene2","o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene3","o23456-compact-first42-20261028-cover_blocks-standard-s0-scene0","o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene1","o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene2","o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene3","o23456-compact-first42-20261028-deposit_coin-standard-s0-scene0","o23456-compact-first42-20261028-fasten_screws-standard-s0-scene0","o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene1","o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene2","o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene3","o23456-compact-first42-20261028-fill_egg_holder-standard-s0-scene0","o23456-compact-first42-20261028-fill_pen_holder-standard-s0-scene0","o23456-compact-first42-20261028-fold_clothes-random-s0-scene0","o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene0","o23456-compact-dev69-20261029-fold_clothes-random-s0-scene1","o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene1","o23456-compact-first42-20261028-general_pickup-standard-s0-scene0","o23456-compact-dev69-20261029-general_pickup-standard-s0-scene1","o23456-compact-dev69-20261029-general_pickup-standard-s0-scene2","o23456-compact-dev69-20261029-general_pickup-standard-s0-scene3","o23456-compact-first42-20261028-hang_mugs-random-s0-scene0","o23456-compact-first42-20261028-imitate_sorting_sequence-standard-s0-scene0","o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene1","o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene2","o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene3","o23456-compact-first42-20261028-insert_key-standard-s0-scene0","o23456-compact-first42-20261028-insert_tubes-standard-s0-scene0","o23456-compact-first42-20261028-make_kong-standard-s0-scene0","o23456-compact-first42-20261028-make_toast-random-s0-scene0","o23456-compact-first42-20261028-match_and_pick_from_conveyor-standard-s0-scene0","o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene1","o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene2","o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene3","o23456-compact-first42-20261028-organize_table-standard-s0-scene0","o23456-compact-first42-20261028-pack_objects_into_box-random-s0-scene0","o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene0","o23456-compact-dev69-20261029-pack_objects_into_box-random-s0-scene1","o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene1","o23456-compact-first42-20261028-pick_from_conveyor_by_image-standard-s0-scene0","o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene1","o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene2","o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene3","o23456-compact-first42-20261028-play_Xylophone-standard-s0-scene0","o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene1","o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene2","o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene3","o23456-compact-first42-20261028-play_stacking_toy-standard-s0-scene0","o23456-compact-first42-20261028-play_tic_tac_toe-standard-s0-scene0","o23456-compact-first42-20261028-plug_in_charger-standard-s0-scene0","o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene1","o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene2","o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene3","o23456-compact-first42-20261028-pour_balls_into_vase-standard-s0-scene0","o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene1","o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene2","o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene3","o23456-compact-first42-20261028-pour_by_language-standard-s0-scene0","o23456-compact-first42-20261028-pour_liquid_into_cup-random-s0-scene0","o23456-compact-first42-20261028-press_by_number-standard-s0-scene0","o23456-compact-dev69-20261029-press_by_number-standard-s0-scene1","o23456-compact-dev69-rerun-20261030-press_by_number-standard-s0-scene2","o23456-compact-dev69-rerun-20261030-press_by_number-standard-s0-scene3","o23456-compact-first42-20261028-push_T-random-s0-scene0","o23456-compact-dev69-20261029-push_T-standard-s0-scene0","o23456-compact-dev69-20261029-push_T-random-s0-scene1","o23456-compact-dev69-20261029-push_T-standard-s0-scene1","o23456-compact-first42-20261028-put_bottles_into_dustbin-standard-s0-scene0","o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene1","o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene2","o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene3","o23456-compact-first42-20261028-solve_equation-standard-s0-scene0","o23456-compact-dev69-20261029-solve_equation-standard-s0-scene1","o23456-compact-dev69-20261029-solve_equation-standard-s0-scene2","o23456-compact-dev69-20261029-solve_equation-standard-s0-scene3","o23456-compact-first42-20261028-sort_nesting_dolls_by_size-random-s0-scene0","o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene0","o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-random-s0-scene1","o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene1","o23456-compact-first42-20261028-stack_blocks-random-s0-scene0","o23456-compact-first42-20261028-stack_blocks_by_language-standard-s0-scene0","o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene1","o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene2","o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene3","o23456-compact-first42-20261028-stack_bowls-random-s0-scene0","o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene0","o23456-compact-dev69-20261029-stack_bowls-random-s0-scene1","o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene1","o23456-compact-first42-20261028-store_laptop_and_headphones-random-s0-scene0","o23456-compact-first42-20261028-store_tools_in_toolbox-standard-s0-scene0","o23456-compact-first42-20261028-swap_T-standard-s0-scene0","o23456-compact-dev69-20261029-swap_T-standard-s0-scene1","o23456-compact-dev69-20261029-swap_T-standard-s0-scene2","o23456-compact-dev69-20261029-swap_T-standard-s0-scene3","o23456-compact-first42-20261028-swap_blocks-standard-s0-scene0","o23456-compact-first42-20261028-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.34791666666666665,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-align_blocks-standard-s0-scene0","o23456-compact-dev69-20261029-align_blocks-standard-s0-scene1","o23456-compact-dev69-20261029-align_blocks-standard-s0-scene2","o23456-compact-dev69-20261029-align_blocks-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-arrange_largest_number-random-s0-scene0","o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene0","o23456-compact-dev69-20261029-arrange_largest_number-random-s0-scene1","o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-classify_objects-standard-s0-scene0","o23456-compact-dev69-20261029-classify_objects-standard-s0-scene1","o23456-compact-dev69-20261029-classify_objects-standard-s0-scene2","o23456-compact-dev69-20261029-classify_objects-standard-s0-scene3"],"score":0.7875,"success_rate":0.75,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-classify_objects_by_language-standard-s0-scene0","o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene1","o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene2","o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene3"],"score":0.2,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-cover_blocks-standard-s0-scene0","o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene1","o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene2","o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-deposit_coin-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-fasten_screws-standard-s0-scene0","o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene1","o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene2","o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene3"],"score":0.675,"success_rate":0.5,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-fold_clothes-random-s0-scene0","o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene0","o23456-compact-dev69-20261029-fold_clothes-random-s0-scene1","o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene1"],"score":0.4,"success_rate":0.25,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-general_pickup-standard-s0-scene0","o23456-compact-dev69-20261029-general_pickup-standard-s0-scene1","o23456-compact-dev69-20261029-general_pickup-standard-s0-scene2","o23456-compact-dev69-20261029-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-imitate_sorting_sequence-standard-s0-scene0","o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene1","o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene2","o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene3"],"score":0.65,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-match_and_pick_from_conveyor-standard-s0-scene0","o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene1","o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene2","o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-pack_objects_into_box-random-s0-scene0","o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene0","o23456-compact-dev69-20261029-pack_objects_into_box-random-s0-scene1","o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene1"],"score":0.5,"success_rate":0.25,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-pick_from_conveyor_by_image-standard-s0-scene0","o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene1","o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene2","o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-play_Xylophone-standard-s0-scene0","o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene1","o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene2","o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-plug_in_charger-standard-s0-scene0","o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene1","o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene2","o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-pour_balls_into_vase-standard-s0-scene0","o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene1","o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene2","o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-press_by_number-standard-s0-scene0","o23456-compact-dev69-20261029-press_by_number-standard-s0-scene1","o23456-compact-dev69-rerun-20261030-press_by_number-standard-s0-scene2","o23456-compact-dev69-rerun-20261030-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-push_T-random-s0-scene0","o23456-compact-dev69-20261029-push_T-standard-s0-scene0","o23456-compact-dev69-20261029-push_T-random-s0-scene1","o23456-compact-dev69-20261029-push_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-put_bottles_into_dustbin-standard-s0-scene0","o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene1","o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene2","o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-solve_equation-standard-s0-scene0","o23456-compact-dev69-20261029-solve_equation-standard-s0-scene1","o23456-compact-dev69-20261029-solve_equation-standard-s0-scene2","o23456-compact-dev69-20261029-solve_equation-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-sort_nesting_dolls_by_size-random-s0-scene0","o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene0","o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-random-s0-scene1","o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-stack_blocks_by_language-standard-s0-scene0","o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene1","o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene2","o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene3"],"score":0.8,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-stack_bowls-random-s0-scene0","o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene0","o23456-compact-dev69-20261029-stack_bowls-random-s0-scene1","o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-compact-first42-20261028-swap_T-standard-s0-scene0","o23456-compact-dev69-20261029-swap_T-standard-s0-scene1","o23456-compact-dev69-20261029-swap_T-standard-s0-scene2","o23456-compact-dev69-20261029-swap_T-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.43333333333333335,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2875,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.7166666666666667,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.53125,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.30625,"success_rate":0.25}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.45499999999999996,"selected_run_ids":["o23456-compact-first42-20261028-align_blocks-standard-s0-scene0","o23456-compact-first42-20261028-arrange_largest_number-random-s0-scene0","o23456-compact-first42-20261028-build_tower-standard-s0-scene0","o23456-compact-first42-20261028-classify_objects-standard-s0-scene0","o23456-compact-first42-20261028-classify_objects_by_language-standard-s0-scene0","o23456-compact-first42-20261028-cover_blocks-standard-s0-scene0","o23456-compact-first42-20261028-deposit_coin-standard-s0-scene0","o23456-compact-first42-20261028-fasten_screws-standard-s0-scene0","o23456-compact-first42-20261028-fill_egg_holder-standard-s0-scene0","o23456-compact-first42-20261028-fill_pen_holder-standard-s0-scene0","o23456-compact-first42-20261028-fold_clothes-random-s0-scene0","o23456-compact-first42-20261028-general_pickup-standard-s0-scene0","o23456-compact-first42-20261028-hang_mugs-random-s0-scene0","o23456-compact-first42-20261028-imitate_sorting_sequence-standard-s0-scene0","o23456-compact-first42-20261028-insert_key-standard-s0-scene0","o23456-compact-first42-20261028-insert_tubes-standard-s0-scene0","o23456-compact-first42-20261028-make_kong-standard-s0-scene0","o23456-compact-first42-20261028-make_toast-random-s0-scene0","o23456-compact-first42-20261028-match_and_pick_from_conveyor-standard-s0-scene0","o23456-compact-first42-20261028-organize_table-standard-s0-scene0","o23456-compact-first42-20261028-pack_objects_into_box-random-s0-scene0","o23456-compact-first42-20261028-pick_from_conveyor_by_image-standard-s0-scene0","o23456-compact-first42-20261028-play_Xylophone-standard-s0-scene0","o23456-compact-first42-20261028-play_stacking_toy-standard-s0-scene0","o23456-compact-first42-20261028-play_tic_tac_toe-standard-s0-scene0","o23456-compact-first42-20261028-plug_in_charger-standard-s0-scene0","o23456-compact-first42-20261028-pour_balls_into_vase-standard-s0-scene0","o23456-compact-first42-20261028-pour_by_language-standard-s0-scene0","o23456-compact-first42-20261028-pour_liquid_into_cup-random-s0-scene0","o23456-compact-first42-20261028-press_by_number-standard-s0-scene0","o23456-compact-first42-20261028-push_T-random-s0-scene0","o23456-compact-first42-20261028-put_bottles_into_dustbin-standard-s0-scene0","o23456-compact-first42-20261028-solve_equation-standard-s0-scene0","o23456-compact-first42-20261028-sort_nesting_dolls_by_size-random-s0-scene0","o23456-compact-first42-20261028-stack_blocks-random-s0-scene0","o23456-compact-first42-20261028-stack_blocks_by_language-standard-s0-scene0","o23456-compact-first42-20261028-stack_bowls-random-s0-scene0","o23456-compact-first42-20261028-store_laptop_and_headphones-random-s0-scene0","o23456-compact-first42-20261028-store_tools_in_toolbox-standard-s0-scene0","o23456-compact-first42-20261028-swap_T-standard-s0-scene0","o23456-compact-first42-20261028-swap_blocks-standard-s0-scene0","o23456-compact-first42-20261028-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.39166666666666666,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-classify_objects_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-deposit_coin-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-fasten_screws-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-imitate_sorting_sequence-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pack_objects_into_box-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-swap_T-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.41250000000000003,"success_rate":0.375},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2875,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6916666666666668,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.44375,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.275,"success_rate":0.1875}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.4220833333333333,"selected_run_ids":["o23456-compact-first42-20261028-align_blocks-standard-s0-scene0","o23456-compact-dev69-20261029-align_blocks-standard-s0-scene1","o23456-compact-first42-20261028-arrange_largest_number-random-s0-scene0","o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene0","o23456-compact-first42-20261028-build_tower-standard-s0-scene0","o23456-compact-first42-20261028-classify_objects-standard-s0-scene0","o23456-compact-dev69-20261029-classify_objects-standard-s0-scene1","o23456-compact-first42-20261028-classify_objects_by_language-standard-s0-scene0","o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene1","o23456-compact-first42-20261028-cover_blocks-standard-s0-scene0","o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene1","o23456-compact-first42-20261028-deposit_coin-standard-s0-scene0","o23456-compact-first42-20261028-fasten_screws-standard-s0-scene0","o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene1","o23456-compact-first42-20261028-fill_egg_holder-standard-s0-scene0","o23456-compact-first42-20261028-fill_pen_holder-standard-s0-scene0","o23456-compact-first42-20261028-fold_clothes-random-s0-scene0","o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene0","o23456-compact-first42-20261028-general_pickup-standard-s0-scene0","o23456-compact-dev69-20261029-general_pickup-standard-s0-scene1","o23456-compact-first42-20261028-hang_mugs-random-s0-scene0","o23456-compact-first42-20261028-imitate_sorting_sequence-standard-s0-scene0","o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene1","o23456-compact-first42-20261028-insert_key-standard-s0-scene0","o23456-compact-first42-20261028-insert_tubes-standard-s0-scene0","o23456-compact-first42-20261028-make_kong-standard-s0-scene0","o23456-compact-first42-20261028-make_toast-random-s0-scene0","o23456-compact-first42-20261028-match_and_pick_from_conveyor-standard-s0-scene0","o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene1","o23456-compact-first42-20261028-organize_table-standard-s0-scene0","o23456-compact-first42-20261028-pack_objects_into_box-random-s0-scene0","o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene0","o23456-compact-first42-20261028-pick_from_conveyor_by_image-standard-s0-scene0","o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene1","o23456-compact-first42-20261028-play_Xylophone-standard-s0-scene0","o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene1","o23456-compact-first42-20261028-play_stacking_toy-standard-s0-scene0","o23456-compact-first42-20261028-play_tic_tac_toe-standard-s0-scene0","o23456-compact-first42-20261028-plug_in_charger-standard-s0-scene0","o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene1","o23456-compact-first42-20261028-pour_balls_into_vase-standard-s0-scene0","o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene1","o23456-compact-first42-20261028-pour_by_language-standard-s0-scene0","o23456-compact-first42-20261028-pour_liquid_into_cup-random-s0-scene0","o23456-compact-first42-20261028-press_by_number-standard-s0-scene0","o23456-compact-dev69-20261029-press_by_number-standard-s0-scene1","o23456-compact-first42-20261028-push_T-random-s0-scene0","o23456-compact-dev69-20261029-push_T-standard-s0-scene0","o23456-compact-first42-20261028-put_bottles_into_dustbin-standard-s0-scene0","o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene1","o23456-compact-first42-20261028-solve_equation-standard-s0-scene0","o23456-compact-dev69-20261029-solve_equation-standard-s0-scene1","o23456-compact-first42-20261028-sort_nesting_dolls_by_size-random-s0-scene0","o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene0","o23456-compact-first42-20261028-stack_blocks-random-s0-scene0","o23456-compact-first42-20261028-stack_blocks_by_language-standard-s0-scene0","o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene1","o23456-compact-first42-20261028-stack_bowls-random-s0-scene0","o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene0","o23456-compact-first42-20261028-store_laptop_and_headphones-random-s0-scene0","o23456-compact-first42-20261028-store_tools_in_toolbox-standard-s0-scene0","o23456-compact-first42-20261028-swap_T-standard-s0-scene0","o23456-compact-dev69-20261029-swap_T-standard-s0-scene1","o23456-compact-first42-20261028-swap_blocks-standard-s0-scene0","o23456-compact-first42-20261028-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3458333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-align_blocks-standard-s0-scene0","o23456-compact-dev69-20261029-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-arrange_largest_number-random-s0-scene0","o23456-compact-dev69-20261029-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-classify_objects-standard-s0-scene0","o23456-compact-dev69-20261029-classify_objects-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-classify_objects_by_language-standard-s0-scene0","o23456-compact-dev69-20261029-classify_objects_by_language-standard-s0-scene1"],"score":0.2,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-cover_blocks-standard-s0-scene0","o23456-compact-dev69-20261029-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-deposit_coin-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-fasten_screws-standard-s0-scene0","o23456-compact-dev69-20261029-fasten_screws-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-fold_clothes-random-s0-scene0","o23456-compact-dev69-20261029-fold_clothes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-general_pickup-standard-s0-scene0","o23456-compact-dev69-20261029-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-imitate_sorting_sequence-standard-s0-scene0","o23456-compact-dev69-20261029-imitate_sorting_sequence-standard-s0-scene1"],"score":0.65,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-insert_tubes-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-match_and_pick_from_conveyor-standard-s0-scene0","o23456-compact-dev69-20261029-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-pack_objects_into_box-random-s0-scene0","o23456-compact-dev69-20261029-pack_objects_into_box-standard-s0-scene0"],"score":0.75,"success_rate":0.5,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-pick_from_conveyor_by_image-standard-s0-scene0","o23456-compact-dev69-20261029-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-play_Xylophone-standard-s0-scene0","o23456-compact-dev69-20261029-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-plug_in_charger-standard-s0-scene0","o23456-compact-dev69-20261029-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-pour_balls_into_vase-standard-s0-scene0","o23456-compact-dev69-20261029-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-press_by_number-standard-s0-scene0","o23456-compact-dev69-20261029-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-push_T-random-s0-scene0","o23456-compact-dev69-20261029-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-put_bottles_into_dustbin-standard-s0-scene0","o23456-compact-dev69-20261029-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-solve_equation-standard-s0-scene0","o23456-compact-dev69-20261029-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-sort_nesting_dolls_by_size-random-s0-scene0","o23456-compact-dev69-20261029-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-stack_blocks_by_language-standard-s0-scene0","o23456-compact-dev69-20261029-stack_blocks_by_language-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-stack_bowls-random-s0-scene0","o23456-compact-dev69-20261029-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-store_tools_in_toolbox-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-compact-first42-20261028-swap_T-standard-s0-scene0","o23456-compact-dev69-20261029-swap_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-compact-first42-20261028-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"cf0e0b22470e4994ced313d04f5843bcfe0ef154ac328cb19eec4ecb9bebc7e5","name":"o23456-compact · 首轮42 + 补充69","selection_id":"o23456-compact-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.35000000000000003,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2375,"success_rate":0.09375},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.42291666666666666,"success_rate":0.375},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.465625,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.06875,"success_rate":0.0}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.30895833333333333,"selected_run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-align_blocks-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene2","depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-arrange_largest_number-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab5-arrange_largest_number-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-build_tower-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-classify_objects-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab5-classify_objects-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-classify_objects-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-classify_objects-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-classify_objects_by_language-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-cover_blocks-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene2","depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-deposit_coin-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fasten_screws-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_egg_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_pen_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fold_clothes-random-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-standard-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-random-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-fold_clothes-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-general_pickup-standard-s0-scene0","depthpro6fig-cuda18-stability-refill16-20261027T141000-general_pickup-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-general_pickup-standard-s0-scene2","depthpro6fig-cuda18-stability-sam300-20261027T182500-general_pickup-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-hang_mugs-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-imitate_sorting_sequence-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_key-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_tubes-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_kong-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_toast-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-match_and_pick_from_conveyor-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene2","depthpro6fig-cuda-human-retry15-complete-20261028T112000-match_and_pick_from_conveyor-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-organize_table-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pack_objects_into_box-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pick_from_conveyor_by_image-standard-s0-scene0","depthpro6fig-cuda18-stability-refill16-20261027T141000-pick_from_conveyor_by_image-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-pick_from_conveyor_by_image-standard-s0-scene2","depthpro6fig-cuda18-stability-sam300-20261027T182500-pick_from_conveyor_by_image-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_Xylophone-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_stacking_toy-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_tic_tac_toe-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-plug_in_charger-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-plug_in_charger-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_balls_into_vase-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_by_language-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_liquid_into_cup-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-press_by_number-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-press_by_number-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-push_T-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab1-push_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-push_T-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-push_T-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-put_bottles_into_dustbin-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab5-put_bottles_into_dustbin-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-solve_equation-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sort_nesting_dolls_by_size-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks_by_language-standard-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-stack_blocks_by_language-standard-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-stack_blocks_by_language-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-stack_blocks_by_language-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_bowls-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_laptop_and_headphones-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_tools_in_toolbox-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene3","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_blocks-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.24791666666666665,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-align_blocks-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene2","depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-arrange_largest_number-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab5-arrange_largest_number-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-classify_objects-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab5-classify_objects-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-classify_objects-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-classify_objects-standard-s0-scene3"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-classify_objects_by_language-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene3"],"score":0.47500000000000003,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-cover_blocks-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene2","depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene3"],"score":0.2625,"success_rate":0.25,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fasten_screws-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene3"],"score":0.1,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fold_clothes-random-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-standard-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-random-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-fold_clothes-standard-s0-scene1"],"score":0.8,"success_rate":0.75,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-general_pickup-standard-s0-scene0","depthpro6fig-cuda18-stability-refill16-20261027T141000-general_pickup-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-general_pickup-standard-s0-scene2","depthpro6fig-cuda18-stability-sam300-20261027T182500-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-imitate_sorting_sequence-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene3"],"score":0.525,"success_rate":0.25,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-match_and_pick_from_conveyor-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene2","depthpro6fig-cuda-human-retry15-complete-20261028T112000-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pack_objects_into_box-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene1"],"score":0.15,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pick_from_conveyor_by_image-standard-s0-scene0","depthpro6fig-cuda18-stability-refill16-20261027T141000-pick_from_conveyor_by_image-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-pick_from_conveyor_by_image-standard-s0-scene2","depthpro6fig-cuda18-stability-sam300-20261027T182500-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_Xylophone-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-plug_in_charger-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-plug_in_charger-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_balls_into_vase-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-press_by_number-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene1","depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-push_T-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab1-push_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-push_T-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-push_T-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-put_bottles_into_dustbin-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab5-put_bottles_into_dustbin-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-solve_equation-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sort_nesting_dolls_by_size-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks_by_language-standard-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-stack_blocks_by_language-standard-s0-scene1","depthpro6fig-cuda-followup17-sim51-20261027T234500-stack_blocks_by_language-standard-s0-scene2","depthpro6fig-cuda-followup17-sim51-20261027T234500-stack_blocks_by_language-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_bowls-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-random-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene1"],"score":0.75,"success_rate":0.75,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene2","o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.35000000000000003,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.25625,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.4166666666666667,"success_rate":0.3333333333333333},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.425,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.05625,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.30083333333333334,"selected_run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-align_blocks-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-arrange_largest_number-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-build_tower-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-classify_objects-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-classify_objects_by_language-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-cover_blocks-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-deposit_coin-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fasten_screws-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_egg_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_pen_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fold_clothes-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-general_pickup-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-hang_mugs-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-imitate_sorting_sequence-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_key-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_tubes-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_kong-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_toast-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-match_and_pick_from_conveyor-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-organize_table-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pack_objects_into_box-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pick_from_conveyor_by_image-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_Xylophone-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_stacking_toy-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_tic_tac_toe-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-plug_in_charger-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_balls_into_vase-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_by_language-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_liquid_into_cup-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-press_by_number-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-push_T-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-put_bottles_into_dustbin-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-solve_equation-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sort_nesting_dolls_by_size-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks_by_language-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_bowls-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_laptop_and_headphones-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_tools_in_toolbox-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_blocks-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2333333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-classify_objects-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fasten_screws-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-imitate_sorting_sequence-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pack_objects_into_box-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-press_by_number-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.3416666666666666,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.29375,"success_rate":0.1875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.4041666666666666,"success_rate":0.3333333333333333},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.40625,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.06875,"success_rate":0.0}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.3029166666666666,"selected_run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-align_blocks-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-arrange_largest_number-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-build_tower-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-classify_objects-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab5-classify_objects-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-classify_objects_by_language-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-cover_blocks-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-deposit_coin-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fasten_screws-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_egg_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_pen_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fold_clothes-random-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-general_pickup-standard-s0-scene0","depthpro6fig-cuda18-stability-refill16-20261027T141000-general_pickup-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-hang_mugs-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-imitate_sorting_sequence-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_key-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_tubes-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_kong-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_toast-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-match_and_pick_from_conveyor-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-organize_table-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pack_objects_into_box-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pick_from_conveyor_by_image-standard-s0-scene0","depthpro6fig-cuda18-stability-refill16-20261027T141000-pick_from_conveyor_by_image-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_Xylophone-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_stacking_toy-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_tic_tac_toe-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-plug_in_charger-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_balls_into_vase-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_by_language-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_liquid_into_cup-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-press_by_number-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-push_T-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab1-push_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-put_bottles_into_dustbin-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-solve_equation-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sort_nesting_dolls_by_size-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks_by_language-standard-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-stack_blocks_by_language-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_bowls-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_laptop_and_headphones-random-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_tools_in_toolbox-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene1","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_blocks-standard-s0-scene0","o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2458333333333333,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-align_blocks-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-arrange_largest_number-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-classify_objects-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab5-classify_objects-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-classify_objects_by_language-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-classify_objects_by_language-standard-s0-scene1"],"score":0.25,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-cover_blocks-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-cover_blocks-standard-s0-scene1"],"score":0.525,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fasten_screws-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-fasten_screws-standard-s0-scene1"],"score":0.1,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-fold_clothes-random-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-fold_clothes-standard-s0-scene0"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-general_pickup-standard-s0-scene0","depthpro6fig-cuda18-stability-refill16-20261027T141000-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-sanity2-20261027-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-imitate_sorting_sequence-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-imitate_sorting_sequence-standard-s0-scene1"],"score":0.4,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-match_and_pick_from_conveyor-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pack_objects_into_box-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-pack_objects_into_box-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pick_from_conveyor_by_image-standard-s0-scene0","depthpro6fig-cuda18-stability-refill16-20261027T141000-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_Xylophone-standard-s0-scene0","depthpro6fig-cuda-followup17-sim51-20261027T234500-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-plug_in_charger-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab3-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_balls_into_vase-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab2-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-press_by_number-standard-s0-scene0","depthpro6fig-cuda18-stability-sam300-20261027T182500-press_by_number-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-push_T-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab1-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-put_bottles_into_dustbin-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-solve_equation-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-solve_equation-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sort_nesting_dolls_by_size-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_blocks_by_language-standard-s0-scene0","depthpro6fig-cuda-followup17-sam300-20261027T225000-stack_blocks_by_language-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-stack_bowls-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-stab4-swap_T-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-nativecontext-first42-dev15-20261027-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"f43c2624d14b3b7c76f29fc35f662822e4ad7c5cd93972c06caf448e1f46602c","name":"o23456-depthpro-6fig-cuda-v1","selection_id":"o23456-depthpro-6fig-cuda-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":3,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":3,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null}},"completed":44,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["o23456-depthpro-6fig-cuda-v1-init2-align_blocks-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-align_blocks-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-align_blocks-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-align_blocks-standard-s0-scene3","o23456-depthpro-6fig-cuda-v1-init2-build_tower-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-classify_objects-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-cover_blocks-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-cover_blocks-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-cover_blocks-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-cover_blocks-standard-s0-scene3","o23456-depthpro-6fig-cuda-v1-init2-fasten_screws-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fill_egg_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fill_pen_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fold_clothes-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-general_pickup-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-general_pickup-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-general_pickup-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-general_pickup-standard-s0-scene3","o23456-depthpro-6fig-cuda-v1-init2-insert_key-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-insert_tubes-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-match_and_pick_from_conveyor-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-match_and_pick_from_conveyor-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-match_and_pick_from_conveyor-standard-s0-scene2","depthpro6fig-cuda18-hilbert11-20261026T191600-match_and_pick_from_conveyor-standard-s0-scene3","o23456-depthpro-6fig-cuda-v1-init2-organize_table-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pack_objects_into_box-random-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-pick_from_conveyor_by_image-standard-s0-scene1","depthpro6fig-cuda18-hilbert13-20261026-pick_from_conveyor_by_image-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-pick_from_conveyor_by_image-standard-s0-scene3","o23456-depthpro-6fig-cuda-v1-init2-play_Xylophone-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-play_tic_tac_toe-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-plug_in_charger-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pour_balls_into_vase-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pour_liquid_into_cup-random-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-press_by_number-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-press_by_number-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-press_by_number-standard-s0-scene3","o23456-depthpro-6fig-cuda-v1-init2-put_bottles_into_dustbin-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-solve_equation-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-sort_nesting_dolls_by_size-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-stack_blocks-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-store_laptop_and_headphones-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-swap_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-align_blocks-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-align_blocks-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-align_blocks-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-align_blocks-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-cover_blocks-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-cover_blocks-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-cover_blocks-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-cover_blocks-standard-s0-scene3"],"score":0.325,"success_rate":0.25,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-general_pickup-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-general_pickup-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-general_pickup-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-match_and_pick_from_conveyor-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-match_and_pick_from_conveyor-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-match_and_pick_from_conveyor-standard-s0-scene2","depthpro6fig-cuda18-hilbert11-20261026T191600-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":3,"expected":4,"run_ids":["depthpro6fig-cuda18-single-gpu-20261026-pick_from_conveyor_by_image-standard-s0-scene1","depthpro6fig-cuda18-hilbert13-20261026-pick_from_conveyor_by_image-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-pick_from_conveyor_by_image-standard-s0-scene3"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":3,"expected":4,"run_ids":["depthpro6fig-cuda18-single-gpu-20261026-press_by_number-standard-s0-scene1","depthpro6fig-cuda18-extra-six-graphics-20261026-press_by_number-standard-s0-scene2","depthpro6fig-cuda18-final-six-20261026-press_by_number-standard-s0-scene3"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":4,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":7,"expected_tasks":8,"score":null,"success_rate":null}},"completed":26,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["o23456-depthpro-6fig-cuda-v1-init2-align_blocks-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-build_tower-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-classify_objects-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-cover_blocks-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fasten_screws-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fill_egg_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fill_pen_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fold_clothes-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-general_pickup-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-insert_key-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-insert_tubes-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-match_and_pick_from_conveyor-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-organize_table-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pack_objects_into_box-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-play_Xylophone-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-play_tic_tac_toe-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-plug_in_charger-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pour_balls_into_vase-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pour_liquid_into_cup-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-put_bottles_into_dustbin-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-solve_equation-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-sort_nesting_dolls_by_size-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-stack_blocks-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-store_laptop_and_headphones-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-swap_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-classify_objects-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-cover_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fasten_screws-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pack_objects_into_box-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":3,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":3,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null}},"completed":32,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["o23456-depthpro-6fig-cuda-v1-init2-align_blocks-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-align_blocks-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-init2-build_tower-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-classify_objects-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-cover_blocks-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-cover_blocks-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-init2-fasten_screws-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fill_egg_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fill_pen_holder-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-fold_clothes-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-general_pickup-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-general_pickup-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-init2-insert_key-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-insert_tubes-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-match_and_pick_from_conveyor-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-match_and_pick_from_conveyor-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-init2-organize_table-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pack_objects_into_box-random-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-pick_from_conveyor_by_image-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-init2-play_Xylophone-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-play_tic_tac_toe-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-plug_in_charger-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pour_balls_into_vase-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-pour_liquid_into_cup-random-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-press_by_number-standard-s0-scene1","o23456-depthpro-6fig-cuda-v1-init2-put_bottles_into_dustbin-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-solve_equation-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-sort_nesting_dolls_by_size-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-stack_blocks-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-store_laptop_and_headphones-random-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-swap_T-standard-s0-scene0","o23456-depthpro-6fig-cuda-v1-init2-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-align_blocks-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-build_tower-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-cover_blocks-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-cover_blocks-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-general_pickup-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-match_and_pick_from_conveyor-standard-s0-scene0","depthpro6fig-cuda18-single-gpu-20261026-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["depthpro6fig-cuda18-single-gpu-20261026-pick_from_conveyor_by_image-standard-s0-scene1"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-play_tic_tac_toe-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["depthpro6fig-cuda18-single-gpu-20261026-press_by_number-standard-s0-scene1"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-stack_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-6fig-cuda-v1-init2-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"33ce26b33d5b71e5fa5f96022001c3c7599db0043c2126630b431ef1481f4aeb","name":"o23456-depthpro-6fig-cuda-48k","selection_id":"o23456-depthpro-6fig-cuda-v1-init2"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":17,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":["o23456-depthpro-cap20-20261024-align_blocks-standard-s0-scene0","o23456-depthpro-cap20-20261024-classify_objects_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-cover_blocks-standard-s0-scene0","o23456-depthpro-cap20-20261024-general_pickup-standard-s0-scene0","o23456-depthpro-cap20-20261024-imitate_sorting_sequence-standard-s0-scene0","o23456-depthpro-cap20-20261024-make_kong-standard-s0-scene0","o23456-depthpro-cap20-20261024-match_and_pick_from_conveyor-standard-s0-scene0","o23456-depthpro-cap20-20261024-organize_table-standard-s0-scene0","o23456-depthpro-cap20-20261024-pick_from_conveyor_by_image-standard-s0-scene0","o23456-depthpro-cap20-20261024-play_stacking_toy-standard-s0-scene0","o23456-depthpro-cap20-20261024-pour_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-press_by_number-standard-s0-scene0","o23456-depthpro-cap20-20261024-solve_equation-standard-s0-scene0","o23456-depthpro-cap20-20261024-stack_blocks_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-store_tools_in_toolbox-standard-s0-scene0","o23456-depthpro-cap20-20261024-swap_T-standard-s0-scene0","o23456-depthpro-cap20-20261024-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["o23456-depthpro-cap20-20261024-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.35833333333333334,"success_rate":0.3333333333333333},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.4,"success_rate":0.375},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":17,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":["o23456-depthpro-cap20-20261024-align_blocks-standard-s0-scene0","o23456-depthpro-cap20-20261024-classify_objects_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-cover_blocks-standard-s0-scene0","o23456-depthpro-cap20-20261024-general_pickup-standard-s0-scene0","o23456-depthpro-cap20-20261024-imitate_sorting_sequence-standard-s0-scene0","o23456-depthpro-cap20-20261024-make_kong-standard-s0-scene0","o23456-depthpro-cap20-20261024-match_and_pick_from_conveyor-standard-s0-scene0","o23456-depthpro-cap20-20261024-organize_table-standard-s0-scene0","o23456-depthpro-cap20-20261024-pick_from_conveyor_by_image-standard-s0-scene0","o23456-depthpro-cap20-20261024-play_stacking_toy-standard-s0-scene0","o23456-depthpro-cap20-20261024-pour_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-press_by_number-standard-s0-scene0","o23456-depthpro-cap20-20261024-solve_equation-standard-s0-scene0","o23456-depthpro-cap20-20261024-stack_blocks_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-store_tools_in_toolbox-standard-s0-scene0","o23456-depthpro-cap20-20261024-swap_T-standard-s0-scene0","o23456-depthpro-cap20-20261024-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-align_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-cover_blocks-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-imitate_sorting_sequence-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-stack_blocks_by_language-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":3,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":17,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["o23456-depthpro-cap20-20261024-align_blocks-standard-s0-scene0","o23456-depthpro-cap20-20261024-classify_objects_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-cover_blocks-standard-s0-scene0","o23456-depthpro-cap20-20261024-general_pickup-standard-s0-scene0","o23456-depthpro-cap20-20261024-imitate_sorting_sequence-standard-s0-scene0","o23456-depthpro-cap20-20261024-make_kong-standard-s0-scene0","o23456-depthpro-cap20-20261024-match_and_pick_from_conveyor-standard-s0-scene0","o23456-depthpro-cap20-20261024-organize_table-standard-s0-scene0","o23456-depthpro-cap20-20261024-pick_from_conveyor_by_image-standard-s0-scene0","o23456-depthpro-cap20-20261024-play_stacking_toy-standard-s0-scene0","o23456-depthpro-cap20-20261024-pour_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-press_by_number-standard-s0-scene0","o23456-depthpro-cap20-20261024-solve_equation-standard-s0-scene0","o23456-depthpro-cap20-20261024-stack_blocks_by_language-standard-s0-scene0","o23456-depthpro-cap20-20261024-store_tools_in_toolbox-standard-s0-scene0","o23456-depthpro-cap20-20261024-swap_T-standard-s0-scene0","o23456-depthpro-cap20-20261024-swap_blocks-standard-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["o23456-depthpro-cap20-20261024-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["o23456-depthpro-cap20-20261024-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"aa7ced0d46d71543351e745e8d1726fc45eccef6f0d3380923304c4a8f8c335c","name":"O23456-depthpro · 协作分工17项","selection_id":"o23456-depthpro-cap20-20261024"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":0,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"P50_111","score":null,"selected_run_ids":[],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":4,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":0,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"first_round","score":null,"selected_run_ids":[],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":0,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":0,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":0,"expected_tasks":8,"score":null,"success_rate":null}},"completed":0,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":[],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"build_tower"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"deposit_coin"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"fill_pen_holder"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"hang_mugs"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_key"},{"capability":"Precision","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_kong"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"make_toast"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"organize_table"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_by_language"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks"},{"capability":"Open","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":0,"expected":2,"run_ids":[],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"swap_blocks"},{"capability":"Generalization","completed":0,"expected":1,"run_ids":[],"score":null,"success_rate":null,"task":"sweep_blocks"}]}},"experiment_id":"aa01bf4fdc68f1a8f479afa9d32306149cb575583895c4142323b8f280aaed84","name":"persistent-cap20-random-scene4（错场景）","selection_id":"persistent-cap20-random-scene4"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"includes_user_accepted_supplementary","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["thunlp-cap20-medium-local13-20261013-align_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-arrange_largest_number-random-s0-scene0","thunlp-cap20-medium-retry9-20261013-build_tower-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-classify_objects-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-classify_objects_by_language-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-cover_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-deposit_coin-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fasten_screws-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-fill_egg_holder-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fill_pen_holder-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fold_clothes-random-s0-scene0","thunlp-cap20-medium-local13-20261013-general_pickup-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-hang_mugs-random-s0-scene0","thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-insert_key-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-insert_tubes-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-make_kong-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-make_toast-random-s0-scene0","thunlp-cap20-medium-retry9-20261013-match_and_pick_from_conveyor-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-organize_table-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-pack_objects_into_box-random-s0-scene0","thunlp-cap20-medium-local13-20261013-pick_from_conveyor_by_image-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-play_Xylophone-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-play_stacking_toy-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-play_tic_tac_toe-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-plug_in_charger-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-pour_balls_into_vase-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-pour_by_language-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-pour_liquid_into_cup-random-s0-scene0","thunlp-cap20-medium-local13-20261013-press_by_number-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-push_T-random-s0-scene0","thunlp-cap20-medium-local42-20261012-put_bottles_into_dustbin-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-solve_equation-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","thunlp-cap20-medium-20261012-stackblocks-repair01-stack_blocks-random-s0-scene0","thunlp-cap20-medium-local13-20261013-stack_blocks_by_language-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-stack_bowls-random-s0-scene0","thunlp-cap20-medium-local42-20261012-store_laptop_and_headphones-random-s0-scene0","thunlp-cap20-medium-local13-20261013-store_tools_in_toolbox-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-swap_T-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-swap_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":["thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0"],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-retry9-20261013-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-retry9-20261013-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-retry9-20261013-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-20261012-stackblocks-repair01-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local42-20261012-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["thunlp-cap20-medium-local13-20261013-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.39999999999999997,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.17500000000000002,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.55,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.08125,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"includes_user_accepted_supplementary","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.3745833333333333,"selected_run_ids":["thunlp-cap20-medium-local13-20261013-align_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-arrange_largest_number-random-s0-scene0","thunlp-cap20-medium-retry9-20261013-build_tower-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-classify_objects-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-classify_objects_by_language-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-cover_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-deposit_coin-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fasten_screws-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-fill_egg_holder-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fill_pen_holder-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fold_clothes-random-s0-scene0","thunlp-cap20-medium-local13-20261013-general_pickup-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-hang_mugs-random-s0-scene0","thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-insert_key-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-insert_tubes-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-make_kong-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-make_toast-random-s0-scene0","thunlp-cap20-medium-retry9-20261013-match_and_pick_from_conveyor-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-organize_table-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-pack_objects_into_box-random-s0-scene0","thunlp-cap20-medium-local13-20261013-pick_from_conveyor_by_image-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-play_Xylophone-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-play_stacking_toy-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-play_tic_tac_toe-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-plug_in_charger-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-pour_balls_into_vase-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-pour_by_language-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-pour_liquid_into_cup-random-s0-scene0","thunlp-cap20-medium-local13-20261013-press_by_number-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-push_T-random-s0-scene0","thunlp-cap20-medium-local42-20261012-put_bottles_into_dustbin-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-solve_equation-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","thunlp-cap20-medium-20261012-stackblocks-repair01-stack_blocks-random-s0-scene0","thunlp-cap20-medium-local13-20261013-stack_blocks_by_language-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-stack_bowls-random-s0-scene0","thunlp-cap20-medium-local42-20261012-store_laptop_and_headphones-random-s0-scene0","thunlp-cap20-medium-local13-20261013-store_tools_in_toolbox-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-swap_T-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-swap_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3,"supplementary_run_ids":["thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0"],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-arrange_largest_number-random-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-fasten_screws-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-pack_objects_into_box-random-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-20261012-stackblocks-repair01-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"includes_user_accepted_supplementary","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["thunlp-cap20-medium-local13-20261013-align_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-arrange_largest_number-random-s0-scene0","thunlp-cap20-medium-retry9-20261013-build_tower-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-classify_objects-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-classify_objects_by_language-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-cover_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-deposit_coin-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fasten_screws-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-fill_egg_holder-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fill_pen_holder-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-fold_clothes-random-s0-scene0","thunlp-cap20-medium-local13-20261013-general_pickup-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-hang_mugs-random-s0-scene0","thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-insert_key-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-insert_tubes-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-make_kong-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-make_toast-random-s0-scene0","thunlp-cap20-medium-retry9-20261013-match_and_pick_from_conveyor-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-organize_table-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-pack_objects_into_box-random-s0-scene0","thunlp-cap20-medium-local13-20261013-pick_from_conveyor_by_image-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-play_Xylophone-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-play_stacking_toy-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-play_tic_tac_toe-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-plug_in_charger-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-pour_balls_into_vase-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-pour_by_language-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-pour_liquid_into_cup-random-s0-scene0","thunlp-cap20-medium-local13-20261013-press_by_number-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-push_T-random-s0-scene0","thunlp-cap20-medium-local42-20261012-put_bottles_into_dustbin-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-solve_equation-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-sort_nesting_dolls_by_size-random-s0-scene0","thunlp-cap20-medium-20261012-stackblocks-repair01-stack_blocks-random-s0-scene0","thunlp-cap20-medium-local13-20261013-stack_blocks_by_language-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-stack_bowls-random-s0-scene0","thunlp-cap20-medium-local42-20261012-store_laptop_and_headphones-random-s0-scene0","thunlp-cap20-medium-local13-20261013-store_tools_in_toolbox-standard-s0-scene0","thunlp-cap20-medium-local13-20261013-swap_T-standard-s0-scene0","thunlp-cap20-medium-retry9-20261013-swap_blocks-standard-s0-scene0","thunlp-cap20-medium-local42-20261012-sweep_blocks-random-s0-scene0"],"status":"incomplete","success_rate":null,"supplementary_run_ids":["thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0"],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-align_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-arrange_largest_number-random-s0-scene0"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-build_tower-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-classify_objects-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-classify_objects_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-retry9-20261013-cover_blocks-standard-s0-scene0"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-fasten_screws-standard-s0-scene0"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-fill_pen_holder-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-fold_clothes-random-s0-scene0"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-general_pickup-standard-s0-scene0"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-imitate_sorting_sequence-standard-s0-scene0"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-retry9-20261013-match_and_pick_from_conveyor-standard-s0-scene0"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-organize_table-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-pack_objects_into_box-random-s0-scene0"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-pick_from_conveyor_by_image-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-play_Xylophone-standard-s0-scene0"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-plug_in_charger-standard-s0-scene0"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-retry9-20261013-pour_balls_into_vase-standard-s0-scene0"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-press_by_number-standard-s0-scene0"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-push_T-random-s0-scene0"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-put_bottles_into_dustbin-standard-s0-scene0"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-solve_equation-standard-s0-scene0"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-sort_nesting_dolls_by_size-random-s0-scene0"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-20261012-stackblocks-repair01-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-stack_blocks_by_language-standard-s0-scene0"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local42-20261012-stack_bowls-random-s0-scene0"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local13-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["thunlp-cap20-medium-local13-20261013-swap_T-standard-s0-scene0"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-retry9-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-cap20-medium-local42-20261012-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"1109062ce749d3e10a55ab49923978a5edb1c79ffbe34da30a0482405eeea924","name":"persistent-cap20-rerun","selection_id":"persistent-cap20-rerun"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"P50_111","score":null,"selected_run_ids":["nocap-import-l3_persistent_v1_align_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_arrange_largest_number_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_build_tower_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_classify_objects_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_classify_objects_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_cover_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_deposit_coin_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fasten_screws_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fill_egg_holder_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fill_pen_holder_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fold_clothes_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_hang_mugs_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_imitate_sorting_sequence_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_insert_key_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_insert_tubes_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_make_kong_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_make_toast_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_match_and_pick_from_conveyor_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_organize_table_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pack_objects_into_box_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pick_from_conveyor_by_image_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_Xylophone_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_stacking_toy_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_tic_tac_toe_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_plug_in_charger_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_balls_into_vase_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_liquid_into_cup_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_press_by_number_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_push_T_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_put_bottles_into_dustbin_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_solve_equation_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_blocks_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_bowls_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_store_laptop_and_headphones_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_store_tools_in_toolbox_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_swap_T_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_swap_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_sweep_blocks_random_s0_layout0_20261002_v1"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_align_blocks_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_arrange_largest_number_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_build_tower_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_classify_objects_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_classify_objects_by_language_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_cover_blocks_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_deposit_coin_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_fasten_screws_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_fill_egg_holder_s0_layout0_20261002_v1"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_fill_pen_holder_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_fold_clothes_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_general_pickup_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_hang_mugs_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_imitate_sorting_sequence_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_insert_key_s0_layout0_20261002_v1"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_insert_tubes_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_make_kong_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_make_toast_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_match_and_pick_from_conveyor_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_organize_table_s0_layout0_20261002_v1"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_pack_objects_into_box_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_pick_from_conveyor_by_image_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_play_Xylophone_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_play_stacking_toy_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_play_tic_tac_toe_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_plug_in_charger_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_pour_balls_into_vase_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pour_by_language_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pour_liquid_into_cup_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_press_by_number_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_push_T_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_put_bottles_into_dustbin_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_solve_equation_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_stack_blocks_random_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_stack_bowls_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_store_laptop_and_headphones_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_store_tools_in_toolbox_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":4,"run_ids":["nocap-import-l3_persistent_v1_swap_T_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_swap_blocks_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_sweep_blocks_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.37083333333333335,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.15625,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.5,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.15625,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.37,"selected_run_ids":["nocap-import-l3_persistent_v1_align_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_arrange_largest_number_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_build_tower_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_classify_objects_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_classify_objects_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_cover_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_deposit_coin_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fasten_screws_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fill_egg_holder_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fill_pen_holder_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fold_clothes_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_hang_mugs_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_imitate_sorting_sequence_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_insert_key_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_insert_tubes_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_make_kong_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_make_toast_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_match_and_pick_from_conveyor_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_organize_table_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pack_objects_into_box_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pick_from_conveyor_by_image_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_Xylophone_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_stacking_toy_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_tic_tac_toe_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_plug_in_charger_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_balls_into_vase_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_liquid_into_cup_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_press_by_number_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_push_T_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_put_bottles_into_dustbin_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_solve_equation_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_blocks_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_bowls_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_store_laptop_and_headphones_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_store_tools_in_toolbox_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_swap_T_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_swap_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_sweep_blocks_random_s0_layout0_20261002_v1"],"status":"complete","success_rate":0.325,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_align_blocks_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_arrange_largest_number_random_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_build_tower_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_classify_objects_s0_layout0_20261002_v1"],"score":0.15,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_classify_objects_by_language_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_cover_blocks_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_deposit_coin_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_fasten_screws_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_fill_egg_holder_s0_layout0_20261002_v1"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_fill_pen_holder_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_fold_clothes_random_s0_layout0_20261002_v1"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_general_pickup_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_hang_mugs_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_imitate_sorting_sequence_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_insert_key_s0_layout0_20261002_v1"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_insert_tubes_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_make_kong_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_make_toast_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_match_and_pick_from_conveyor_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_organize_table_s0_layout0_20261002_v1"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pack_objects_into_box_random_s0_layout0_20261002_v1"],"score":0.25,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pick_from_conveyor_by_image_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_play_Xylophone_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_play_stacking_toy_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_play_tic_tac_toe_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_plug_in_charger_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pour_balls_into_vase_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pour_by_language_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pour_liquid_into_cup_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_press_by_number_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_push_T_random_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_put_bottles_into_dustbin_s0_layout0_20261002_v1"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_solve_equation_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_stack_blocks_random_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_stack_bowls_random_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_store_laptop_and_headphones_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_store_tools_in_toolbox_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_swap_T_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_swap_blocks_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_sweep_blocks_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":6,"expected_tasks":12,"score":null,"success_rate":null},"Long-Horizon":{"completed_tasks":6,"expected_tasks":8,"score":null,"success_rate":null},"Memory":{"completed_tasks":1,"expected_tasks":6,"score":null,"success_rate":null},"Open":{"completed_tasks":2,"expected_tasks":8,"score":null,"success_rate":null},"Precision":{"completed_tasks":4,"expected_tasks":8,"score":null,"success_rate":null}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"}],"plan_id":"spiky2_65","score":null,"selected_run_ids":["nocap-import-l3_persistent_v1_align_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_arrange_largest_number_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_build_tower_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_classify_objects_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_classify_objects_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_cover_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_deposit_coin_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fasten_screws_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fill_egg_holder_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fill_pen_holder_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_fold_clothes_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_general_pickup_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_hang_mugs_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_imitate_sorting_sequence_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_insert_key_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_insert_tubes_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_make_kong_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_make_toast_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_match_and_pick_from_conveyor_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_organize_table_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pack_objects_into_box_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pick_from_conveyor_by_image_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_Xylophone_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_stacking_toy_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_play_tic_tac_toe_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_plug_in_charger_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_balls_into_vase_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_pour_liquid_into_cup_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_press_by_number_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_push_T_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_put_bottles_into_dustbin_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_solve_equation_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_blocks_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_stack_bowls_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_store_laptop_and_headphones_random_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_store_tools_in_toolbox_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_swap_T_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_swap_blocks_s0_layout0_20261002_v1","nocap-import-l3_persistent_v1_sweep_blocks_random_s0_layout0_20261002_v1"],"status":"incomplete","success_rate":null,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_align_blocks_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_arrange_largest_number_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_build_tower_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_classify_objects_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_classify_objects_by_language_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_cover_blocks_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_deposit_coin_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_fasten_screws_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_fill_egg_holder_s0_layout0_20261002_v1"],"score":0.25,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_fill_pen_holder_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_fold_clothes_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_general_pickup_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_hang_mugs_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_imitate_sorting_sequence_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_insert_key_s0_layout0_20261002_v1"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_insert_tubes_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_make_kong_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_make_toast_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_match_and_pick_from_conveyor_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_organize_table_s0_layout0_20261002_v1"],"score":0.25,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_pack_objects_into_box_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_pick_from_conveyor_by_image_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_play_Xylophone_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_play_stacking_toy_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_play_tic_tac_toe_s0_layout0_20261002_v1"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_plug_in_charger_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_pour_balls_into_vase_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pour_by_language_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_pour_liquid_into_cup_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_press_by_number_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_push_T_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_put_bottles_into_dustbin_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_solve_equation_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_stack_blocks_random_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_stack_blocks_by_language_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_stack_bowls_random_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_store_laptop_and_headphones_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_store_tools_in_toolbox_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":2,"run_ids":["nocap-import-l3_persistent_v1_swap_T_s0_layout0_20261002_v1"],"score":null,"success_rate":null,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_swap_blocks_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["nocap-import-l3_persistent_v1_sweep_blocks_random_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"b38355a9f7dfb9ca45d6592cbc796b413274de34c79b67f99365fa14e447aa42","name":"persistent-nocap medium: R1, 30 standard + 12 random Generalization; seed0 scene0","selection_id":"persistent-nocap-medium-mixed42-v1"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.36041666666666666,"success_rate":0.2916666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2453125,"success_rate":0.0625},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.525,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.509375,"success_rate":0.46875},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.09375,"success_rate":0.03125}},"completed":111,"conflicts":[],"evidence_basis":"includes_user_accepted_supplementary","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.34677083333333336,"selected_run_ids":["thunlp-full-ik42-medium-20261013-align_blocks-standard-s0-scene0","medium-nocap-dev63-20261102-align_blocks-standard-s0-scene1","medium-nocap-dev63-20261102-align_blocks-standard-s0-scene2","medium-nocap-dev63-20261102-align_blocks-standard-s0-scene3","thunlp-full-ik42-medium-20261013-arrange_largest_number-random-s0-scene0","nocap-import-l3_persistent_v1_arrange_largest_number_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-arrange_largest_number-random-s0-scene1","medium-nocap-dev63-20261102-arrange_largest_number-standard-s0-scene1","thunlp-full-ik42-medium-20261013-build_tower-standard-s0-scene0","thunlp-full-ik42-medium-20261013-classify_objects-standard-s0-scene0","medium-nocap-dev63-20261102-classify_objects-standard-s0-scene1","medium-nocap-dev63-20261102-classify_objects-standard-s0-scene2","medium-nocap-dev63-20261102-classify_objects-standard-s0-scene3","thunlp-full-ik42-medium-20261013-classify_objects_by_language-standard-s0-scene0","medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene1","medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene2","medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene3","thunlp-full-ik42-medium-20261013-cover_blocks-standard-s0-scene0","medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene1","medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene2","medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene3","thunlp-full-ik42-medium-20261013-deposit_coin-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fasten_screws-standard-s0-scene0","medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene1","medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene2","medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene3","thunlp-full-ik42-medium-20261013-fill_egg_holder-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fill_pen_holder-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fold_clothes-random-s0-scene0","nocap-import-l3_persistent_v1_fold_clothes_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-fold_clothes-random-s0-scene1","medium-nocap-dev63-20261102-fold_clothes-standard-s0-scene1","thunlp-full-ik42-medium-20261013-general_pickup-standard-s0-scene0","medium-nocap-dev63-20261102-general_pickup-standard-s0-scene1","medium-nocap-dev63-20261102-general_pickup-standard-s0-scene2","medium-nocap-dev63-20261102-general_pickup-standard-s0-scene3","thunlp-full-ik7-retry01-20261014-hang_mugs-random-s0-scene0","thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0","medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene1","medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene2","medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene3","thunlp-full-ik42-medium-20261013-insert_key-standard-s0-scene0","thunlp-full-ik42-medium-20261013-insert_tubes-standard-s0-scene0","thunlp-full-ik42-medium-20261013-make_kong-standard-s0-scene0","thunlp-full-ik42-medium-20261013-make_toast-random-s0-scene0","thunlp-full-ik42-medium-20261013-match_and_pick_from_conveyor-standard-s0-scene0","medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene1","medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene2","medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene3","thunlp-full-ik42-medium-20261013-organize_table-standard-s0-scene0","thunlp-full-ik3-retry02-20261014-pack_objects_into_box-random-s0-scene0","nocap-import-l3_persistent_v1_pack_objects_into_box_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-pack_objects_into_box-random-s0-scene1","medium-nocap-dev63-20261102-pack_objects_into_box-standard-s0-scene1","thunlp-full-ik42-medium-20261013-pick_from_conveyor_by_image-standard-s0-scene0","medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene1","medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene2","medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene3","thunlp-full-ik42-medium-20261013-play_Xylophone-standard-s0-scene0","medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene1","medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene2","medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene3","thunlp-full-ik42-medium-20261013-play_stacking_toy-standard-s0-scene0","thunlp-full-ik42-medium-20261013-play_tic_tac_toe-standard-s0-scene0","thunlp-full-ik7-retry01-20261014-plug_in_charger-standard-s0-scene0","medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene1","medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene2","medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene3","thunlp-full-ik42-medium-20261013-pour_balls_into_vase-standard-s0-scene0","medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene1","medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene2","medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene3","thunlp-full-ik42-medium-20261013-pour_by_language-standard-s0-scene0","thunlp-full-ik42-medium-20261013-pour_liquid_into_cup-random-s0-scene0","thunlp-full-ik42-medium-20261013-press_by_number-standard-s0-scene0","medium-nocap-dev63-20261102-press_by_number-standard-s0-scene1","medium-nocap-dev63-20261102-press_by_number-standard-s0-scene2","medium-nocap-dev63-20261102-press_by_number-standard-s0-scene3","thunlp-full-ik7-retry01-20261014-push_T-random-s0-scene0","nocap-import-l3_persistent_v1_push_T_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-push_T-random-s0-scene1","medium-nocap-dev63-20261102-push_T-standard-s0-scene1","thunlp-full-ik42-medium-20261013-put_bottles_into_dustbin-standard-s0-scene0","medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene1","medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene2","medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene3","thunlp-full-ik42-medium-20261013-solve_equation-standard-s0-scene0","medium-nocap-dev63-20261102-solve_equation-standard-s0-scene1","medium-nocap-dev63-20261102-solve_equation-standard-s0-scene2","medium-nocap-dev63-20261102-solve_equation-standard-s0-scene3","thunlp-full-ik42-medium-20261013-sort_nesting_dolls_by_size-random-s0-scene0","nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-sort_nesting_dolls_by_size-random-s0-scene1","medium-nocap-dev63-20261102-sort_nesting_dolls_by_size-standard-s0-scene1","thunlp-full-ik42-medium-20261013-stack_blocks-random-s0-scene0","thunlp-full-ik42-medium-20261013-stack_blocks_by_language-standard-s0-scene0","medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene1","medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene2","medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene3","thunlp-full-ik3-retry02-20261014-stack_bowls-random-s0-scene0","nocap-import-l3_persistent_v1_stack_bowls_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-stack_bowls-random-s0-scene1","medium-nocap-dev63-20261102-stack_bowls-standard-s0-scene1","thunlp-full-ik7-retry01-20261014-store_laptop_and_headphones-random-s0-scene0","thunlp-full-ik42-medium-20261013-store_tools_in_toolbox-standard-s0-scene0","thunlp-full-ik42-medium-20261013-swap_T-standard-s0-scene0","medium-nocap-dev63-20261102-swap_T-standard-s0-scene1","medium-nocap-dev63-20261102-swap_T-standard-s0-scene2","medium-nocap-dev63-20261102-swap_T-standard-s0-scene3","thunlp-full-ik42-medium-20261013-swap_blocks-standard-s0-scene0","thunlp-full-ik3-retry02-20261014-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.27083333333333337,"supplementary_run_ids":["thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0"],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-align_blocks-standard-s0-scene0","medium-nocap-dev63-20261102-align_blocks-standard-s0-scene1","medium-nocap-dev63-20261102-align_blocks-standard-s0-scene2","medium-nocap-dev63-20261102-align_blocks-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-arrange_largest_number-random-s0-scene0","nocap-import-l3_persistent_v1_arrange_largest_number_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-arrange_largest_number-random-s0-scene1","medium-nocap-dev63-20261102-arrange_largest_number-standard-s0-scene1"],"score":0.6375,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-classify_objects-standard-s0-scene0","medium-nocap-dev63-20261102-classify_objects-standard-s0-scene1","medium-nocap-dev63-20261102-classify_objects-standard-s0-scene2","medium-nocap-dev63-20261102-classify_objects-standard-s0-scene3"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-classify_objects_by_language-standard-s0-scene0","medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene1","medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene2","medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene3"],"score":0.47500000000000003,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-cover_blocks-standard-s0-scene0","medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene1","medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene2","medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene3"],"score":0.4,"success_rate":0.25,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-fasten_screws-standard-s0-scene0","medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene1","medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene2","medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene3"],"score":0.25,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-fold_clothes-random-s0-scene0","nocap-import-l3_persistent_v1_fold_clothes_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-fold_clothes-random-s0-scene1","medium-nocap-dev63-20261102-fold_clothes-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-general_pickup-standard-s0-scene0","medium-nocap-dev63-20261102-general_pickup-standard-s0-scene1","medium-nocap-dev63-20261102-general_pickup-standard-s0-scene2","medium-nocap-dev63-20261102-general_pickup-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik7-retry01-20261014-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0","medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene1","medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene2","medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-match_and_pick_from_conveyor-standard-s0-scene0","medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene1","medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene2","medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["thunlp-full-ik3-retry02-20261014-pack_objects_into_box-random-s0-scene0","nocap-import-l3_persistent_v1_pack_objects_into_box_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-pack_objects_into_box-random-s0-scene1","medium-nocap-dev63-20261102-pack_objects_into_box-standard-s0-scene1"],"score":0.3,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-pick_from_conveyor_by_image-standard-s0-scene0","medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene1","medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene2","medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-play_Xylophone-standard-s0-scene0","medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene1","medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene2","medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["thunlp-full-ik7-retry01-20261014-plug_in_charger-standard-s0-scene0","medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene1","medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene2","medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-pour_balls_into_vase-standard-s0-scene0","medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene1","medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene2","medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-pour_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-press_by_number-standard-s0-scene0","medium-nocap-dev63-20261102-press_by_number-standard-s0-scene1","medium-nocap-dev63-20261102-press_by_number-standard-s0-scene2","medium-nocap-dev63-20261102-press_by_number-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["thunlp-full-ik7-retry01-20261014-push_T-random-s0-scene0","nocap-import-l3_persistent_v1_push_T_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-push_T-random-s0-scene1","medium-nocap-dev63-20261102-push_T-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-put_bottles_into_dustbin-standard-s0-scene0","medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene1","medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene2","medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.36250000000000004,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-solve_equation-standard-s0-scene0","medium-nocap-dev63-20261102-solve_equation-standard-s0-scene1","medium-nocap-dev63-20261102-solve_equation-standard-s0-scene2","medium-nocap-dev63-20261102-solve_equation-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-sort_nesting_dolls_by_size-random-s0-scene0","nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-sort_nesting_dolls_by_size-random-s0-scene1","medium-nocap-dev63-20261102-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-stack_blocks_by_language-standard-s0-scene0","medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene1","medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene2","medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene3"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["thunlp-full-ik3-retry02-20261014-stack_bowls-random-s0-scene0","nocap-import-l3_persistent_v1_stack_bowls_s0_layout0_20261002_v1","medium-nocap-dev63-20261102-stack_bowls-random-s0-scene1","medium-nocap-dev63-20261102-stack_bowls-standard-s0-scene1"],"score":0.5375,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik7-retry01-20261014-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["thunlp-full-ik42-medium-20261013-swap_T-standard-s0-scene0","medium-nocap-dev63-20261102-swap_T-standard-s0-scene1","medium-nocap-dev63-20261102-swap_T-standard-s0-scene2","medium-nocap-dev63-20261102-swap_T-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik3-retry02-20261014-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.45416666666666666,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2125,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.625,"success_rate":0.625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.21875,"success_rate":0.125}},"completed":42,"conflicts":[],"evidence_basis":"includes_user_accepted_supplementary","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.4354166666666667,"selected_run_ids":["thunlp-full-ik42-medium-20261013-align_blocks-standard-s0-scene0","thunlp-full-ik42-medium-20261013-arrange_largest_number-random-s0-scene0","thunlp-full-ik42-medium-20261013-build_tower-standard-s0-scene0","thunlp-full-ik42-medium-20261013-classify_objects-standard-s0-scene0","thunlp-full-ik42-medium-20261013-classify_objects_by_language-standard-s0-scene0","thunlp-full-ik42-medium-20261013-cover_blocks-standard-s0-scene0","thunlp-full-ik42-medium-20261013-deposit_coin-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fasten_screws-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fill_egg_holder-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fill_pen_holder-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fold_clothes-random-s0-scene0","thunlp-full-ik42-medium-20261013-general_pickup-standard-s0-scene0","thunlp-full-ik7-retry01-20261014-hang_mugs-random-s0-scene0","thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0","thunlp-full-ik42-medium-20261013-insert_key-standard-s0-scene0","thunlp-full-ik42-medium-20261013-insert_tubes-standard-s0-scene0","thunlp-full-ik42-medium-20261013-make_kong-standard-s0-scene0","thunlp-full-ik42-medium-20261013-make_toast-random-s0-scene0","thunlp-full-ik42-medium-20261013-match_and_pick_from_conveyor-standard-s0-scene0","thunlp-full-ik42-medium-20261013-organize_table-standard-s0-scene0","thunlp-full-ik3-retry02-20261014-pack_objects_into_box-random-s0-scene0","thunlp-full-ik42-medium-20261013-pick_from_conveyor_by_image-standard-s0-scene0","thunlp-full-ik42-medium-20261013-play_Xylophone-standard-s0-scene0","thunlp-full-ik42-medium-20261013-play_stacking_toy-standard-s0-scene0","thunlp-full-ik42-medium-20261013-play_tic_tac_toe-standard-s0-scene0","thunlp-full-ik7-retry01-20261014-plug_in_charger-standard-s0-scene0","thunlp-full-ik42-medium-20261013-pour_balls_into_vase-standard-s0-scene0","thunlp-full-ik42-medium-20261013-pour_by_language-standard-s0-scene0","thunlp-full-ik42-medium-20261013-pour_liquid_into_cup-random-s0-scene0","thunlp-full-ik42-medium-20261013-press_by_number-standard-s0-scene0","thunlp-full-ik7-retry01-20261014-push_T-random-s0-scene0","thunlp-full-ik42-medium-20261013-put_bottles_into_dustbin-standard-s0-scene0","thunlp-full-ik42-medium-20261013-solve_equation-standard-s0-scene0","thunlp-full-ik42-medium-20261013-sort_nesting_dolls_by_size-random-s0-scene0","thunlp-full-ik42-medium-20261013-stack_blocks-random-s0-scene0","thunlp-full-ik42-medium-20261013-stack_blocks_by_language-standard-s0-scene0","thunlp-full-ik3-retry02-20261014-stack_bowls-random-s0-scene0","thunlp-full-ik7-retry01-20261014-store_laptop_and_headphones-random-s0-scene0","thunlp-full-ik42-medium-20261013-store_tools_in_toolbox-standard-s0-scene0","thunlp-full-ik42-medium-20261013-swap_T-standard-s0-scene0","thunlp-full-ik42-medium-20261013-swap_blocks-standard-s0-scene0","thunlp-full-ik3-retry02-20261014-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.36666666666666664,"supplementary_run_ids":["thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0"],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-fasten_screws-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik7-retry01-20261014-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik3-retry02-20261014-pack_objects_into_box-random-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik7-retry01-20261014-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-pour_balls_into_vase-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-pour_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik7-retry01-20261014-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-sort_nesting_dolls_by_size-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik3-retry02-20261014-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik7-retry01-20261014-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik3-retry02-20261014-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.39375,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2125,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6083333333333333,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.51875,"success_rate":0.5},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.125,"success_rate":0.0625}},"completed":65,"conflicts":[],"evidence_basis":"includes_user_accepted_supplementary","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.3716666666666667,"selected_run_ids":["thunlp-full-ik42-medium-20261013-align_blocks-standard-s0-scene0","medium-nocap-dev63-20261102-align_blocks-standard-s0-scene1","thunlp-full-ik42-medium-20261013-arrange_largest_number-random-s0-scene0","nocap-import-l3_persistent_v1_arrange_largest_number_s0_layout0_20261002_v1","thunlp-full-ik42-medium-20261013-build_tower-standard-s0-scene0","thunlp-full-ik42-medium-20261013-classify_objects-standard-s0-scene0","medium-nocap-dev63-20261102-classify_objects-standard-s0-scene1","thunlp-full-ik42-medium-20261013-classify_objects_by_language-standard-s0-scene0","medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene1","thunlp-full-ik42-medium-20261013-cover_blocks-standard-s0-scene0","medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene1","thunlp-full-ik42-medium-20261013-deposit_coin-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fasten_screws-standard-s0-scene0","medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene1","thunlp-full-ik42-medium-20261013-fill_egg_holder-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fill_pen_holder-standard-s0-scene0","thunlp-full-ik42-medium-20261013-fold_clothes-random-s0-scene0","nocap-import-l3_persistent_v1_fold_clothes_s0_layout0_20261002_v1","thunlp-full-ik42-medium-20261013-general_pickup-standard-s0-scene0","medium-nocap-dev63-20261102-general_pickup-standard-s0-scene1","thunlp-full-ik7-retry01-20261014-hang_mugs-random-s0-scene0","thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0","medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene1","thunlp-full-ik42-medium-20261013-insert_key-standard-s0-scene0","thunlp-full-ik42-medium-20261013-insert_tubes-standard-s0-scene0","thunlp-full-ik42-medium-20261013-make_kong-standard-s0-scene0","thunlp-full-ik42-medium-20261013-make_toast-random-s0-scene0","thunlp-full-ik42-medium-20261013-match_and_pick_from_conveyor-standard-s0-scene0","medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene1","thunlp-full-ik42-medium-20261013-organize_table-standard-s0-scene0","thunlp-full-ik3-retry02-20261014-pack_objects_into_box-random-s0-scene0","nocap-import-l3_persistent_v1_pack_objects_into_box_s0_layout0_20261002_v1","thunlp-full-ik42-medium-20261013-pick_from_conveyor_by_image-standard-s0-scene0","medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene1","thunlp-full-ik42-medium-20261013-play_Xylophone-standard-s0-scene0","medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene1","thunlp-full-ik42-medium-20261013-play_stacking_toy-standard-s0-scene0","thunlp-full-ik42-medium-20261013-play_tic_tac_toe-standard-s0-scene0","thunlp-full-ik7-retry01-20261014-plug_in_charger-standard-s0-scene0","medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene1","thunlp-full-ik42-medium-20261013-pour_balls_into_vase-standard-s0-scene0","medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene1","thunlp-full-ik42-medium-20261013-pour_by_language-standard-s0-scene0","thunlp-full-ik42-medium-20261013-pour_liquid_into_cup-random-s0-scene0","thunlp-full-ik42-medium-20261013-press_by_number-standard-s0-scene0","medium-nocap-dev63-20261102-press_by_number-standard-s0-scene1","thunlp-full-ik7-retry01-20261014-push_T-random-s0-scene0","nocap-import-l3_persistent_v1_push_T_s0_layout0_20261002_v1","thunlp-full-ik42-medium-20261013-put_bottles_into_dustbin-standard-s0-scene0","medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene1","thunlp-full-ik42-medium-20261013-solve_equation-standard-s0-scene0","medium-nocap-dev63-20261102-solve_equation-standard-s0-scene1","thunlp-full-ik42-medium-20261013-sort_nesting_dolls_by_size-random-s0-scene0","nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_s0_layout0_20261002_v1","thunlp-full-ik42-medium-20261013-stack_blocks-random-s0-scene0","thunlp-full-ik42-medium-20261013-stack_blocks_by_language-standard-s0-scene0","medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene1","thunlp-full-ik3-retry02-20261014-stack_bowls-random-s0-scene0","nocap-import-l3_persistent_v1_stack_bowls_s0_layout0_20261002_v1","thunlp-full-ik7-retry01-20261014-store_laptop_and_headphones-random-s0-scene0","thunlp-full-ik42-medium-20261013-store_tools_in_toolbox-standard-s0-scene0","thunlp-full-ik42-medium-20261013-swap_T-standard-s0-scene0","medium-nocap-dev63-20261102-swap_T-standard-s0-scene1","thunlp-full-ik42-medium-20261013-swap_blocks-standard-s0-scene0","thunlp-full-ik3-retry02-20261014-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.29583333333333334,"supplementary_run_ids":["thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0"],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-align_blocks-standard-s0-scene0","medium-nocap-dev63-20261102-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-arrange_largest_number-random-s0-scene0","nocap-import-l3_persistent_v1_arrange_largest_number_s0_layout0_20261002_v1"],"score":0.575,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-classify_objects-standard-s0-scene0","medium-nocap-dev63-20261102-classify_objects-standard-s0-scene1"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-classify_objects_by_language-standard-s0-scene0","medium-nocap-dev63-20261102-classify_objects_by_language-standard-s0-scene1"],"score":0.55,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-cover_blocks-standard-s0-scene0","medium-nocap-dev63-20261102-cover_blocks-standard-s0-scene1"],"score":0.65,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-deposit_coin-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-fasten_screws-standard-s0-scene0","medium-nocap-dev63-20261102-fasten_screws-standard-s0-scene1"],"score":0.25,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-fold_clothes-random-s0-scene0","nocap-import-l3_persistent_v1_fold_clothes_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-general_pickup-standard-s0-scene0","medium-nocap-dev63-20261102-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik7-retry01-20261014-hang_mugs-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["thunlp-full-ik-imitate-retry01-20261014-imitate_sorting_sequence-standard-s0-scene0","medium-nocap-dev63-20261102-imitate_sorting_sequence-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-match_and_pick_from_conveyor-standard-s0-scene0","medium-nocap-dev63-20261102-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["thunlp-full-ik3-retry02-20261014-pack_objects_into_box-random-s0-scene0","nocap-import-l3_persistent_v1_pack_objects_into_box_s0_layout0_20261002_v1"],"score":0.3,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-pick_from_conveyor_by_image-standard-s0-scene0","medium-nocap-dev63-20261102-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-play_Xylophone-standard-s0-scene0","medium-nocap-dev63-20261102-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-play_stacking_toy-standard-s0-scene0"],"score":0.3,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["thunlp-full-ik7-retry01-20261014-plug_in_charger-standard-s0-scene0","medium-nocap-dev63-20261102-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-pour_balls_into_vase-standard-s0-scene0","medium-nocap-dev63-20261102-pour_balls_into_vase-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-pour_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-press_by_number-standard-s0-scene0","medium-nocap-dev63-20261102-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["thunlp-full-ik7-retry01-20261014-push_T-random-s0-scene0","nocap-import-l3_persistent_v1_push_T_s0_layout0_20261002_v1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-put_bottles_into_dustbin-standard-s0-scene0","medium-nocap-dev63-20261102-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-solve_equation-standard-s0-scene0","medium-nocap-dev63-20261102-solve_equation-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-sort_nesting_dolls_by_size-random-s0-scene0","nocap-import-l3_persistent_v1_sort_nesting_dolls_by_size_s0_layout0_20261002_v1"],"score":0.0,"success_rate":0.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-stack_blocks_by_language-standard-s0-scene0","medium-nocap-dev63-20261102-stack_blocks_by_language-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["thunlp-full-ik3-retry02-20261014-stack_bowls-random-s0-scene0","nocap-import-l3_persistent_v1_stack_bowls_s0_layout0_20261002_v1"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik7-retry01-20261014-store_laptop_and_headphones-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["thunlp-full-ik42-medium-20261013-swap_T-standard-s0-scene0","medium-nocap-dev63-20261102-swap_T-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["thunlp-full-ik42-medium-20261013-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["thunlp-full-ik3-retry02-20261014-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"f0ba6a3b6e7c6553d771e41507561cd747d408d7d62bc933b6f8eff3ed5b9040","name":"persistent-nocap-rerun · 首轮42 + 原Devset补集69","selection_id":"persistent-nocap-rerun"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.3520833333333333,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.3734375,"success_rate":0.0625},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5833333333333334,"success_rate":0.5416666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.38125,"success_rate":0.34375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.159375,"success_rate":0.03125}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.3698958333333333,"selected_run_ids":["rsi-final42-995480fe-20261023-c011-align_blocks-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene3","rsi-final42-995480fe-20261023-c030-arrange_largest_number-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene1","rsi-final42-995480fe-20261023-c016-build_tower-standard-s0-scene0","rsi-final42-995480fe-20261023-c007-classify_objects-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene3","rsi-final42-995480fe-20261023-c032-classify_objects_by_language-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene3","rsi-final42-995480fe-20261023-c006-cover_blocks-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene3","rsi-final42-995480fe-20261023-c005-deposit_coin-standard-s0-scene0","rsi-final42-995480fe-20261023-c019-fasten_screws-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene3","rsi-final42-995480fe-20261023-c020-fill_egg_holder-standard-s0-scene0","rsi-final42-995480fe-20261023-c003-fill_pen_holder-standard-s0-scene0","rsi-final42-995480fe-20261023-c022-fold_clothes-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fold_clothes-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene1","rsi-final42-995480fe-20261023-c002-general_pickup-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene3","rsi-final42-995480fe-20261023-c009-hang_mugs-random-s0-scene0","rsi-final42-995480fe-20261023-c038-imitate_sorting_sequence-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene3","rsi-final42-995480fe-20261023-c014-insert_key-standard-s0-scene0","rsi-final42-995480fe-20261023-c010-insert_tubes-standard-s0-scene0","rsi-final42-995480fe-20261023-c028-make_kong-standard-s0-scene0","rsi-final42-995480fe-20261023-c026-make_toast-random-s0-scene0","rsi-final42-995480fe-20261023-c035-match_and_pick_from_conveyor-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene3","rsi-final42-995480fe-20261023-c021-organize_table-standard-s0-scene0","rsi-final42-995480fe-20261023-c017-pack_objects_into_box-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene1","rsi-final42-995480fe-20261023-c040-pick_from_conveyor_by_image-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene3","rsi-final42-995480fe-20261023-c023-play_Xylophone-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene3","rsi-final42-995480fe-20261023-c024-play_stacking_toy-standard-s0-scene0","rsi-final42-995480fe-20261023-c037-play_tic_tac_toe-standard-s0-scene0","rsi-final42-995480fe-20261023-c001-plug_in_charger-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene3","rsi-final42-995480fe-20261023-c015-pour_balls_into_vase-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene3","rsi-final42-995480fe-20261023-c041-pour_by_language-standard-s0-scene0","rsi-final42-995480fe-20261023-c036-pour_liquid_into_cup-random-s0-scene0","rsi-final42-995480fe-20261023-c027-press_by_number-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene3","rsi-final42-995480fe-20261023-c008-push_T-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-push_T-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene1","rsi-final42-995480fe-20261023-c012-put_bottles_into_dustbin-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene3","rsi-final42-995480fe-20261023-c039-solve_equation-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene3","rsi-final42-995480fe-20261023-c018-sort_nesting_dolls_by_size-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene1","rsi-final42-995480fe-20261023-c013-stack_blocks-random-s0-scene0","rsi-final42-995480fe-20261023-c031-stack_blocks_by_language-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene3","rsi-final42-995480fe-20261023-c000-stack_bowls-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_bowls-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene1","rsi-final42-995480fe-20261023-c034-store_laptop_and_headphones-random-s0-scene0","rsi-final42-995480fe-20261023-c033-store_tools_in_toolbox-standard-s0-scene0","rsi-final42-995480fe-20261023-c029-swap_T-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene3","rsi-final42-995480fe-20261023-c025-swap_blocks-standard-s0-scene0","rsi-final42-995480fe-20261023-c004-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2625,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c011-align_blocks-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c030-arrange_largest_number-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c016-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c007-classify_objects-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene3"],"score":0.4875,"success_rate":0.25,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c032-classify_objects_by_language-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene3"],"score":0.30000000000000004,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c006-cover_blocks-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c005-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c019-fasten_screws-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene3"],"score":0.425,"success_rate":0.25,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c020-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c003-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c022-fold_clothes-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fold_clothes-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c002-general_pickup-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c009-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c038-imitate_sorting_sequence-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene3"],"score":0.75,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c014-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c010-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c028-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c026-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c035-match_and_pick_from_conveyor-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c021-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c017-pack_objects_into_box-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene1"],"score":0.0875,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c040-pick_from_conveyor_by_image-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c023-play_Xylophone-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c024-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c037-play_tic_tac_toe-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c001-plug_in_charger-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c015-pour_balls_into_vase-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c041-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c036-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c027-press_by_number-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c008-push_T-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-push_T-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c012-put_bottles_into_dustbin-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.55,"success_rate":0.25,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c039-solve_equation-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c018-sort_nesting_dolls_by_size-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c031-stack_blocks_by_language-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c000-stack_bowls-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_bowls-random-s0-scene1","rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene1"],"score":0.5375,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c034-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c033-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["rsi-final42-995480fe-20261023-c029-swap_T-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene1","rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene2","rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c025-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c004-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.35000000000000003,"success_rate":0.3333333333333333},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.34375,"success_rate":0.0},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6666666666666666,"success_rate":0.6666666666666666},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.425,"success_rate":0.375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.16875,"success_rate":0.0}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.3908333333333333,"selected_run_ids":["rsi-final42-995480fe-20261023-c011-align_blocks-standard-s0-scene0","rsi-final42-995480fe-20261023-c030-arrange_largest_number-random-s0-scene0","rsi-final42-995480fe-20261023-c016-build_tower-standard-s0-scene0","rsi-final42-995480fe-20261023-c007-classify_objects-standard-s0-scene0","rsi-final42-995480fe-20261023-c032-classify_objects_by_language-standard-s0-scene0","rsi-final42-995480fe-20261023-c006-cover_blocks-standard-s0-scene0","rsi-final42-995480fe-20261023-c005-deposit_coin-standard-s0-scene0","rsi-final42-995480fe-20261023-c019-fasten_screws-standard-s0-scene0","rsi-final42-995480fe-20261023-c020-fill_egg_holder-standard-s0-scene0","rsi-final42-995480fe-20261023-c003-fill_pen_holder-standard-s0-scene0","rsi-final42-995480fe-20261023-c022-fold_clothes-random-s0-scene0","rsi-final42-995480fe-20261023-c002-general_pickup-standard-s0-scene0","rsi-final42-995480fe-20261023-c009-hang_mugs-random-s0-scene0","rsi-final42-995480fe-20261023-c038-imitate_sorting_sequence-standard-s0-scene0","rsi-final42-995480fe-20261023-c014-insert_key-standard-s0-scene0","rsi-final42-995480fe-20261023-c010-insert_tubes-standard-s0-scene0","rsi-final42-995480fe-20261023-c028-make_kong-standard-s0-scene0","rsi-final42-995480fe-20261023-c026-make_toast-random-s0-scene0","rsi-final42-995480fe-20261023-c035-match_and_pick_from_conveyor-standard-s0-scene0","rsi-final42-995480fe-20261023-c021-organize_table-standard-s0-scene0","rsi-final42-995480fe-20261023-c017-pack_objects_into_box-random-s0-scene0","rsi-final42-995480fe-20261023-c040-pick_from_conveyor_by_image-standard-s0-scene0","rsi-final42-995480fe-20261023-c023-play_Xylophone-standard-s0-scene0","rsi-final42-995480fe-20261023-c024-play_stacking_toy-standard-s0-scene0","rsi-final42-995480fe-20261023-c037-play_tic_tac_toe-standard-s0-scene0","rsi-final42-995480fe-20261023-c001-plug_in_charger-standard-s0-scene0","rsi-final42-995480fe-20261023-c015-pour_balls_into_vase-standard-s0-scene0","rsi-final42-995480fe-20261023-c041-pour_by_language-standard-s0-scene0","rsi-final42-995480fe-20261023-c036-pour_liquid_into_cup-random-s0-scene0","rsi-final42-995480fe-20261023-c027-press_by_number-standard-s0-scene0","rsi-final42-995480fe-20261023-c008-push_T-random-s0-scene0","rsi-final42-995480fe-20261023-c012-put_bottles_into_dustbin-standard-s0-scene0","rsi-final42-995480fe-20261023-c039-solve_equation-standard-s0-scene0","rsi-final42-995480fe-20261023-c018-sort_nesting_dolls_by_size-random-s0-scene0","rsi-final42-995480fe-20261023-c013-stack_blocks-random-s0-scene0","rsi-final42-995480fe-20261023-c031-stack_blocks_by_language-standard-s0-scene0","rsi-final42-995480fe-20261023-c000-stack_bowls-random-s0-scene0","rsi-final42-995480fe-20261023-c034-store_laptop_and_headphones-random-s0-scene0","rsi-final42-995480fe-20261023-c033-store_tools_in_toolbox-standard-s0-scene0","rsi-final42-995480fe-20261023-c029-swap_T-standard-s0-scene0","rsi-final42-995480fe-20261023-c025-swap_blocks-standard-s0-scene0","rsi-final42-995480fe-20261023-c004-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.275,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c011-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c030-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c016-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c007-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c032-classify_objects_by_language-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c006-cover_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c005-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c019-fasten_screws-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c020-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c003-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c022-fold_clothes-random-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c002-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c009-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c038-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c014-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c010-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c028-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c026-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c035-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c021-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c017-pack_objects_into_box-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c040-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c023-play_Xylophone-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c024-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c037-play_tic_tac_toe-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c001-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c015-pour_balls_into_vase-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c041-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c036-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c027-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c008-push_T-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c012-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c039-solve_equation-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c018-sort_nesting_dolls_by_size-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c031-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c000-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c034-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c033-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c029-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c025-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c004-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.4291666666666667,"success_rate":0.4166666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.41875,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5416666666666666,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.3625,"success_rate":0.3125},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.1375,"success_rate":0.0}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.3779166666666667,"selected_run_ids":["rsi-final42-995480fe-20261023-c011-align_blocks-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene1","rsi-final42-995480fe-20261023-c030-arrange_largest_number-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene0","rsi-final42-995480fe-20261023-c016-build_tower-standard-s0-scene0","rsi-final42-995480fe-20261023-c007-classify_objects-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene1","rsi-final42-995480fe-20261023-c032-classify_objects_by_language-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene1","rsi-final42-995480fe-20261023-c006-cover_blocks-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene1","rsi-final42-995480fe-20261023-c005-deposit_coin-standard-s0-scene0","rsi-final42-995480fe-20261023-c019-fasten_screws-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene1","rsi-final42-995480fe-20261023-c020-fill_egg_holder-standard-s0-scene0","rsi-final42-995480fe-20261023-c003-fill_pen_holder-standard-s0-scene0","rsi-final42-995480fe-20261023-c022-fold_clothes-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene0","rsi-final42-995480fe-20261023-c002-general_pickup-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene1","rsi-final42-995480fe-20261023-c009-hang_mugs-random-s0-scene0","rsi-final42-995480fe-20261023-c038-imitate_sorting_sequence-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene1","rsi-final42-995480fe-20261023-c014-insert_key-standard-s0-scene0","rsi-final42-995480fe-20261023-c010-insert_tubes-standard-s0-scene0","rsi-final42-995480fe-20261023-c028-make_kong-standard-s0-scene0","rsi-final42-995480fe-20261023-c026-make_toast-random-s0-scene0","rsi-final42-995480fe-20261023-c035-match_and_pick_from_conveyor-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene1","rsi-final42-995480fe-20261023-c021-organize_table-standard-s0-scene0","rsi-final42-995480fe-20261023-c017-pack_objects_into_box-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene0","rsi-final42-995480fe-20261023-c040-pick_from_conveyor_by_image-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene1","rsi-final42-995480fe-20261023-c023-play_Xylophone-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene1","rsi-final42-995480fe-20261023-c024-play_stacking_toy-standard-s0-scene0","rsi-final42-995480fe-20261023-c037-play_tic_tac_toe-standard-s0-scene0","rsi-final42-995480fe-20261023-c001-plug_in_charger-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene1","rsi-final42-995480fe-20261023-c015-pour_balls_into_vase-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene1","rsi-final42-995480fe-20261023-c041-pour_by_language-standard-s0-scene0","rsi-final42-995480fe-20261023-c036-pour_liquid_into_cup-random-s0-scene0","rsi-final42-995480fe-20261023-c027-press_by_number-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene1","rsi-final42-995480fe-20261023-c008-push_T-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene0","rsi-final42-995480fe-20261023-c012-put_bottles_into_dustbin-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene1","rsi-final42-995480fe-20261023-c039-solve_equation-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene1","rsi-final42-995480fe-20261023-c018-sort_nesting_dolls_by_size-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene0","rsi-final42-995480fe-20261023-c013-stack_blocks-random-s0-scene0","rsi-final42-995480fe-20261023-c031-stack_blocks_by_language-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene1","rsi-final42-995480fe-20261023-c000-stack_bowls-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene0","rsi-final42-995480fe-20261023-c034-store_laptop_and_headphones-random-s0-scene0","rsi-final42-995480fe-20261023-c033-store_tools_in_toolbox-standard-s0-scene0","rsi-final42-995480fe-20261023-c029-swap_T-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene1","rsi-final42-995480fe-20261023-c025-swap_blocks-standard-s0-scene0","rsi-final42-995480fe-20261023-c004-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.27083333333333337,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c011-align_blocks-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c030-arrange_largest_number-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-arrange_largest_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c016-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c007-classify_objects-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-classify_objects-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c032-classify_objects_by_language-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-classify_objects_by_language-standard-s0-scene1"],"score":0.4,"success_rate":0.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c006-cover_blocks-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-cover_blocks-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c005-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c019-fasten_screws-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fasten_screws-standard-s0-scene1"],"score":0.25,"success_rate":0.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c020-fill_egg_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c003-fill_pen_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c022-fold_clothes-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-fold_clothes-standard-s0-scene0"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c002-general_pickup-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c009-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c038-imitate_sorting_sequence-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-imitate_sorting_sequence-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c014-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c010-insert_tubes-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c028-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c026-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c035-match_and_pick_from_conveyor-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c021-organize_table-standard-s0-scene0"],"score":0.5,"success_rate":0.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c017-pack_objects_into_box-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pack_objects_into_box-standard-s0-scene0"],"score":0.05,"success_rate":0.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c040-pick_from_conveyor_by_image-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c023-play_Xylophone-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-play_Xylophone-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c024-play_stacking_toy-standard-s0-scene0"],"score":0.6,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c037-play_tic_tac_toe-standard-s0-scene0"],"score":0.75,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c001-plug_in_charger-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c015-pour_balls_into_vase-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-pour_balls_into_vase-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c041-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c036-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c027-press_by_number-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-press_by_number-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c008-push_T-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c012-put_bottles_into_dustbin-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c039-solve_equation-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-solve_equation-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c018-sort_nesting_dolls_by_size-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c013-stack_blocks-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c031-stack_blocks_by_language-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_blocks_by_language-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c000-stack_bowls-random-s0-scene0","rsi-semantic-dev69-995480fe-20261101-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c034-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c033-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["rsi-final42-995480fe-20261023-c029-swap_T-standard-s0-scene0","rsi-semantic-dev69-995480fe-20261101-swap_T-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c025-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["rsi-final42-995480fe-20261023-c004-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"5cf299eef0f3c87ea1ed297cbe38a0c889b105bedd2eab559d1f7b7439af378f","name":"RSI Semantic EEF","selection_id":"rsi-semantic-eef"},{"evaluation_scores":{"P50_111":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.2333333333333333,"success_rate":0.1875},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.2875,"success_rate":0.1875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.6104166666666667,"success_rate":0.5833333333333334},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.38125,"success_rate":0.34375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.21875,"success_rate":0.15625}},"completed":111,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":111,"label":"P50_111","missing_cases":[],"plan_id":"P50_111","score":0.34625,"selected_run_ids":["semantic-eef-align-blocks-cap20-20261019-2151-align_blocks-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene3","semantic-eef-arrange-largest-number-cap20-20261019-2151-arrange_largest_number-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene1","semantic-eef-build-tower-cap20-20261019-2151-build_tower-standard-s0-scene0","semantic-eef-classify-cap20-20261019-2039-classify_objects-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene3","semantic-eef-classify-objects-by-language-cap20-20261019-2151-classify_objects_by_language-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene3","semantic-eef-cover-blocks-cap20-20261019-2151-cover_blocks-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene3","semantic-eef-coin-cap20-20261019-1955-deposit_coin-standard-s0-scene0","semantic-eef-fasten-screws-cap20-20261019-2151-fasten_screws-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene3","semantic-eef-fill-egg-holder-cap20-20261019-2151-fill_egg_holder-standard-s0-scene0","semantic-eef-fill-pen-holder-cap20-20261019-2151-fill_pen_holder-standard-s0-scene0","semantic-eef-fold-clothes-cap20-20261019-2151-fold_clothes-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene1","semantic-eef-general-pickup-cap20-20261019-2151-general_pickup-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene3","semantic-eef-hang-mugs-cap20-20261019-2039-hang_mugs-random-s0-scene0","semantic-eef-imitate-sorting-sequence-cap20-20261019-2151-imitate_sorting_sequence-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene3","semantic-eef-insert-key-cap20-20261019-2151-insert_key-standard-s0-scene0","semantic-eef-insert-tubes-cap20-20261019-2039-insert_tubes-standard-s0-scene0","semantic-eef-make-kong-cap20-20261019-2151-make_kong-standard-s0-scene0","semantic-eef-make-toast-cap20-20261019-2151-make_toast-random-s0-scene0","semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151-match_and_pick_from_conveyor-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene3","semantic-eef-organize-table-cap20-20261019-2151-organize_table-standard-s0-scene0","semantic-eef-pack-cap20-20261019-1955-pack_objects_into_box-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene1","semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151-pick_from_conveyor_by_image-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene3","semantic-eef-play-xylophone-cap20-20261019-2151-play_Xylophone-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene3","semantic-eef-play-stacking-toy-cap20-20261019-2151-play_stacking_toy-standard-s0-scene0","semantic-eef-play-tic-tac-toe-cap20-20261019-2151-play_tic_tac_toe-standard-s0-scene0","semantic-eef-plug-charger-cap20-20261019-2123-plug_in_charger-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene3","semantic-eef-pour-cap20-20261019-1955-pour_balls_into_vase-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene3","semantic-eef-pour-by-language-cap20-20261019-2151-pour_by_language-standard-s0-scene0","semantic-eef-pour-liquid-into-cup-cap20-20261019-2151-pour_liquid_into_cup-random-s0-scene0","semantic-eef-press-by-number-cap20-20261019-2151-press_by_number-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene3","semantic-eef-push-t-cap20-retry1-20261019-2247-push_T-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-push_T-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene1","semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151-put_bottles_into_dustbin-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene3","semantic-eef-solve-equation-cap20-20261019-2151-solve_equation-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene3","semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151-sort_nesting_dolls_by_size-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene1","semantic-eef-stack-blocks-cap20-20261019-2151-stack_blocks-random-s0-scene0","semantic-eef-stack-blocks-by-language-cap20-20261019-2151-stack_blocks_by_language-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene3","semantic-eef-stack-bowls-cap20-20261019-2123-stack_bowls-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene1","semantic-eef-store-laptop-and-headphones-cap20-20261019-2151-store_laptop_and_headphones-random-s0-scene0","semantic-eef-store-tools-in-toolbox-cap20-20261019-2151-store_tools_in_toolbox-standard-s0-scene0","semantic-eef-swap-t-cap20-20261019-2151-swap_T-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene3","semantic-eef-swap-blocks-cap20-20261019-2151-swap_blocks-standard-s0-scene0","semantic-eef-sweep-blocks-cap20-20261019-2151-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.2916666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":4,"expected":4,"run_ids":["semantic-eef-align-blocks-cap20-20261019-2151-align_blocks-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene3"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["semantic-eef-arrange-largest-number-cap20-20261019-2151-arrange_largest_number-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene1"],"score":0.6125,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-build-tower-cap20-20261019-2151-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["semantic-eef-classify-cap20-20261019-2039-classify_objects-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene3"],"score":0.6375,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":4,"expected":4,"run_ids":["semantic-eef-classify-objects-by-language-cap20-20261019-2151-classify_objects_by_language-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene3"],"score":0.45,"success_rate":0.25,"task":"classify_objects_by_language"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["semantic-eef-cover-blocks-cap20-20261019-2151-cover_blocks-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene3"],"score":0.5375,"success_rate":0.5,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-coin-cap20-20261019-1955-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["semantic-eef-fasten-screws-cap20-20261019-2151-fasten_screws-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene3"],"score":0.8,"success_rate":0.75,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-fill-egg-holder-cap20-20261019-2151-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-fill-pen-holder-cap20-20261019-2151-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["semantic-eef-fold-clothes-cap20-20261019-2151-fold_clothes-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":4,"expected":4,"run_ids":["semantic-eef-general-pickup-cap20-20261019-2151-general_pickup-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-hang-mugs-cap20-20261019-2039-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["semantic-eef-imitate-sorting-sequence-cap20-20261019-2151-imitate_sorting_sequence-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene3"],"score":0.875,"success_rate":0.75,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-insert-key-cap20-20261019-2151-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-insert-tubes-cap20-20261019-2039-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-make-kong-cap20-20261019-2151-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-make-toast-cap20-20261019-2151-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151-match_and_pick_from_conveyor-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-organize-table-cap20-20261019-2151-organize_table-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"organize_table"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["semantic-eef-pack-cap20-20261019-1955-pack_objects_into_box-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene1"],"score":0.3625,"success_rate":0.25,"task":"pack_objects_into_box"},{"capability":"Open","completed":4,"expected":4,"run_ids":["semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151-pick_from_conveyor_by_image-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["semantic-eef-play-xylophone-cap20-20261019-2151-play_Xylophone-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-play-stacking-toy-cap20-20261019-2151-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-play-tic-tac-toe-cap20-20261019-2151-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["semantic-eef-plug-charger-cap20-20261019-2123-plug_in_charger-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene3"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":4,"expected":4,"run_ids":["semantic-eef-pour-cap20-20261019-1955-pour_balls_into_vase-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-pour-by-language-cap20-20261019-2151-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-pour-liquid-into-cup-cap20-20261019-2151-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["semantic-eef-press-by-number-cap20-20261019-2151-press_by_number-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene3"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["semantic-eef-push-t-cap20-retry1-20261019-2247-push_T-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-push_T-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"push_T"},{"capability":"Long-Horizon","completed":4,"expected":4,"run_ids":["semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151-put_bottles_into_dustbin-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene3"],"score":0.36250000000000004,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":4,"expected":4,"run_ids":["semantic-eef-solve-equation-cap20-20261019-2151-solve_equation-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene3"],"score":0.75,"success_rate":0.75,"task":"solve_equation"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151-sort_nesting_dolls_by_size-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene1"],"score":0.25,"success_rate":0.25,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-stack-blocks-cap20-20261019-2151-stack_blocks-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":4,"expected":4,"run_ids":["semantic-eef-stack-blocks-by-language-cap20-20261019-2151-stack_blocks_by_language-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene3"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":4,"expected":4,"run_ids":["semantic-eef-stack-bowls-cap20-20261019-2123-stack_bowls-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-random-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene1"],"score":0.575,"success_rate":0.5,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-store-laptop-and-headphones-cap20-20261019-2151-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-store-tools-in-toolbox-cap20-20261019-2151-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":4,"expected":4,"run_ids":["semantic-eef-swap-t-cap20-20261019-2151-swap_T-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene1","semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene2","semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene3"],"score":0.25,"success_rate":0.25,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["semantic-eef-swap-blocks-cap20-20261019-2151-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-sweep-blocks-cap20-20261019-2151-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"first_round":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.5125000000000001,"success_rate":0.5},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.24375,"success_rate":0.125},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.5,"success_rate":0.5},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.625,"success_rate":0.625},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.43125,"success_rate":0.375}},"completed":42,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":42,"label":"首轮42","missing_cases":[],"plan_id":"first_round","score":0.4625,"selected_run_ids":["semantic-eef-align-blocks-cap20-20261019-2151-align_blocks-standard-s0-scene0","semantic-eef-arrange-largest-number-cap20-20261019-2151-arrange_largest_number-random-s0-scene0","semantic-eef-build-tower-cap20-20261019-2151-build_tower-standard-s0-scene0","semantic-eef-classify-cap20-20261019-2039-classify_objects-standard-s0-scene0","semantic-eef-classify-objects-by-language-cap20-20261019-2151-classify_objects_by_language-standard-s0-scene0","semantic-eef-cover-blocks-cap20-20261019-2151-cover_blocks-standard-s0-scene0","semantic-eef-coin-cap20-20261019-1955-deposit_coin-standard-s0-scene0","semantic-eef-fasten-screws-cap20-20261019-2151-fasten_screws-standard-s0-scene0","semantic-eef-fill-egg-holder-cap20-20261019-2151-fill_egg_holder-standard-s0-scene0","semantic-eef-fill-pen-holder-cap20-20261019-2151-fill_pen_holder-standard-s0-scene0","semantic-eef-fold-clothes-cap20-20261019-2151-fold_clothes-random-s0-scene0","semantic-eef-general-pickup-cap20-20261019-2151-general_pickup-standard-s0-scene0","semantic-eef-hang-mugs-cap20-20261019-2039-hang_mugs-random-s0-scene0","semantic-eef-imitate-sorting-sequence-cap20-20261019-2151-imitate_sorting_sequence-standard-s0-scene0","semantic-eef-insert-key-cap20-20261019-2151-insert_key-standard-s0-scene0","semantic-eef-insert-tubes-cap20-20261019-2039-insert_tubes-standard-s0-scene0","semantic-eef-make-kong-cap20-20261019-2151-make_kong-standard-s0-scene0","semantic-eef-make-toast-cap20-20261019-2151-make_toast-random-s0-scene0","semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151-match_and_pick_from_conveyor-standard-s0-scene0","semantic-eef-organize-table-cap20-20261019-2151-organize_table-standard-s0-scene0","semantic-eef-pack-cap20-20261019-1955-pack_objects_into_box-random-s0-scene0","semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151-pick_from_conveyor_by_image-standard-s0-scene0","semantic-eef-play-xylophone-cap20-20261019-2151-play_Xylophone-standard-s0-scene0","semantic-eef-play-stacking-toy-cap20-20261019-2151-play_stacking_toy-standard-s0-scene0","semantic-eef-play-tic-tac-toe-cap20-20261019-2151-play_tic_tac_toe-standard-s0-scene0","semantic-eef-plug-charger-cap20-20261019-2123-plug_in_charger-standard-s0-scene0","semantic-eef-pour-cap20-20261019-1955-pour_balls_into_vase-standard-s0-scene0","semantic-eef-pour-by-language-cap20-20261019-2151-pour_by_language-standard-s0-scene0","semantic-eef-pour-liquid-into-cup-cap20-20261019-2151-pour_liquid_into_cup-random-s0-scene0","semantic-eef-press-by-number-cap20-20261019-2151-press_by_number-standard-s0-scene0","semantic-eef-push-t-cap20-retry1-20261019-2247-push_T-random-s0-scene0","semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151-put_bottles_into_dustbin-standard-s0-scene0","semantic-eef-solve-equation-cap20-20261019-2151-solve_equation-standard-s0-scene0","semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151-sort_nesting_dolls_by_size-random-s0-scene0","semantic-eef-stack-blocks-cap20-20261019-2151-stack_blocks-random-s0-scene0","semantic-eef-stack-blocks-by-language-cap20-20261019-2151-stack_blocks_by_language-standard-s0-scene0","semantic-eef-stack-bowls-cap20-20261019-2123-stack_bowls-random-s0-scene0","semantic-eef-store-laptop-and-headphones-cap20-20261019-2151-store_laptop_and_headphones-random-s0-scene0","semantic-eef-store-tools-in-toolbox-cap20-20261019-2151-store_tools_in_toolbox-standard-s0-scene0","semantic-eef-swap-t-cap20-20261019-2151-swap_T-standard-s0-scene0","semantic-eef-swap-blocks-cap20-20261019-2151-swap_blocks-standard-s0-scene0","semantic-eef-sweep-blocks-cap20-20261019-2151-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.425,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-align-blocks-cap20-20261019-2151-align_blocks-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"align_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-arrange-largest-number-cap20-20261019-2151-arrange_largest_number-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-build-tower-cap20-20261019-2151-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-classify-cap20-20261019-2039-classify_objects-standard-s0-scene0"],"score":0.4,"success_rate":0.0,"task":"classify_objects"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-classify-objects-by-language-cap20-20261019-2151-classify_objects_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"classify_objects_by_language"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["semantic-eef-cover-blocks-cap20-20261019-2151-cover_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-coin-cap20-20261019-1955-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-fasten-screws-cap20-20261019-2151-fasten_screws-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-fill-egg-holder-cap20-20261019-2151-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-fill-pen-holder-cap20-20261019-2151-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-fold-clothes-cap20-20261019-2151-fold_clothes-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"fold_clothes"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-general-pickup-cap20-20261019-2151-general_pickup-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-hang-mugs-cap20-20261019-2039-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["semantic-eef-imitate-sorting-sequence-cap20-20261019-2151-imitate_sorting_sequence-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-insert-key-cap20-20261019-2151-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-insert-tubes-cap20-20261019-2039-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-make-kong-cap20-20261019-2151-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-make-toast-cap20-20261019-2151-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151-match_and_pick_from_conveyor-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-organize-table-cap20-20261019-2151-organize_table-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"organize_table"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-pack-cap20-20261019-1955-pack_objects_into_box-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pack_objects_into_box"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151-pick_from_conveyor_by_image-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-play-xylophone-cap20-20261019-2151-play_Xylophone-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-play-stacking-toy-cap20-20261019-2151-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-play-tic-tac-toe-cap20-20261019-2151-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-plug-charger-cap20-20261019-2123-plug_in_charger-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-pour-cap20-20261019-1955-pour_balls_into_vase-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-pour-by-language-cap20-20261019-2151-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-pour-liquid-into-cup-cap20-20261019-2151-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["semantic-eef-press-by-number-cap20-20261019-2151-press_by_number-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-push-t-cap20-retry1-20261019-2247-push_T-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"push_T"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151-put_bottles_into_dustbin-standard-s0-scene0"],"score":0.25,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-solve-equation-cap20-20261019-2151-solve_equation-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151-sort_nesting_dolls_by_size-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-stack-blocks-cap20-20261019-2151-stack_blocks-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-stack-blocks-by-language-cap20-20261019-2151-stack_blocks_by_language-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-stack-bowls-cap20-20261019-2123-stack_bowls-random-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-store-laptop-and-headphones-cap20-20261019-2151-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-store-tools-in-toolbox-cap20-20261019-2151-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["semantic-eef-swap-t-cap20-20261019-2151-swap_T-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["semantic-eef-swap-blocks-cap20-20261019-2151-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-sweep-blocks-cap20-20261019-2151-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]},"spiky2_65":{"capability_scores":{"Generalization":{"completed_tasks":12,"expected_tasks":12,"score":0.32916666666666666,"success_rate":0.2916666666666667},"Long-Horizon":{"completed_tasks":8,"expected_tasks":8,"score":0.290625,"success_rate":0.1875},"Memory":{"completed_tasks":6,"expected_tasks":6,"score":0.4708333333333334,"success_rate":0.4166666666666667},"Open":{"completed_tasks":8,"expected_tasks":8,"score":0.475,"success_rate":0.4375},"Precision":{"completed_tasks":8,"expected_tasks":8,"score":0.30625,"success_rate":0.25}},"completed":65,"conflicts":[],"evidence_basis":"native_only","excluded_records":[],"expected":65,"label":"Spiky-2（65例）","missing_cases":[],"plan_id":"spiky2_65","score":0.374375,"selected_run_ids":["semantic-eef-align-blocks-cap20-20261019-2151-align_blocks-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene1","semantic-eef-arrange-largest-number-cap20-20261019-2151-arrange_largest_number-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene0","semantic-eef-build-tower-cap20-20261019-2151-build_tower-standard-s0-scene0","semantic-eef-classify-cap20-20261019-2039-classify_objects-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene1","semantic-eef-classify-objects-by-language-cap20-20261019-2151-classify_objects_by_language-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene1","semantic-eef-cover-blocks-cap20-20261019-2151-cover_blocks-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene1","semantic-eef-coin-cap20-20261019-1955-deposit_coin-standard-s0-scene0","semantic-eef-fasten-screws-cap20-20261019-2151-fasten_screws-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene1","semantic-eef-fill-egg-holder-cap20-20261019-2151-fill_egg_holder-standard-s0-scene0","semantic-eef-fill-pen-holder-cap20-20261019-2151-fill_pen_holder-standard-s0-scene0","semantic-eef-fold-clothes-cap20-20261019-2151-fold_clothes-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene0","semantic-eef-general-pickup-cap20-20261019-2151-general_pickup-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene1","semantic-eef-hang-mugs-cap20-20261019-2039-hang_mugs-random-s0-scene0","semantic-eef-imitate-sorting-sequence-cap20-20261019-2151-imitate_sorting_sequence-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene1","semantic-eef-insert-key-cap20-20261019-2151-insert_key-standard-s0-scene0","semantic-eef-insert-tubes-cap20-20261019-2039-insert_tubes-standard-s0-scene0","semantic-eef-make-kong-cap20-20261019-2151-make_kong-standard-s0-scene0","semantic-eef-make-toast-cap20-20261019-2151-make_toast-random-s0-scene0","semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151-match_and_pick_from_conveyor-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene1","semantic-eef-organize-table-cap20-20261019-2151-organize_table-standard-s0-scene0","semantic-eef-pack-cap20-20261019-1955-pack_objects_into_box-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene0","semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151-pick_from_conveyor_by_image-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene1","semantic-eef-play-xylophone-cap20-20261019-2151-play_Xylophone-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene1","semantic-eef-play-stacking-toy-cap20-20261019-2151-play_stacking_toy-standard-s0-scene0","semantic-eef-play-tic-tac-toe-cap20-20261019-2151-play_tic_tac_toe-standard-s0-scene0","semantic-eef-plug-charger-cap20-20261019-2123-plug_in_charger-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene1","semantic-eef-pour-cap20-20261019-1955-pour_balls_into_vase-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene1","semantic-eef-pour-by-language-cap20-20261019-2151-pour_by_language-standard-s0-scene0","semantic-eef-pour-liquid-into-cup-cap20-20261019-2151-pour_liquid_into_cup-random-s0-scene0","semantic-eef-press-by-number-cap20-20261019-2151-press_by_number-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene1","semantic-eef-push-t-cap20-retry1-20261019-2247-push_T-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene0","semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151-put_bottles_into_dustbin-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene1","semantic-eef-solve-equation-cap20-20261019-2151-solve_equation-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene1","semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151-sort_nesting_dolls_by_size-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene0","semantic-eef-stack-blocks-cap20-20261019-2151-stack_blocks-random-s0-scene0","semantic-eef-stack-blocks-by-language-cap20-20261019-2151-stack_blocks_by_language-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene1","semantic-eef-stack-bowls-cap20-20261019-2123-stack_bowls-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene0","semantic-eef-store-laptop-and-headphones-cap20-20261019-2151-store_laptop_and_headphones-random-s0-scene0","semantic-eef-store-tools-in-toolbox-cap20-20261019-2151-store_tools_in_toolbox-standard-s0-scene0","semantic-eef-swap-t-cap20-20261019-2151-swap_T-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene1","semantic-eef-swap-blocks-cap20-20261019-2151-swap_blocks-standard-s0-scene0","semantic-eef-sweep-blocks-cap20-20261019-2151-sweep_blocks-random-s0-scene0"],"status":"complete","success_rate":0.3166666666666667,"supplementary_run_ids":[],"task_scores":[{"capability":"Open","completed":2,"expected":2,"run_ids":["semantic-eef-align-blocks-cap20-20261019-2151-align_blocks-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-align_blocks-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"align_blocks"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["semantic-eef-arrange-largest-number-cap20-20261019-2151-arrange_largest_number-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-arrange_largest_number-standard-s0-scene0"],"score":0.65,"success_rate":0.5,"task":"arrange_largest_number"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-build-tower-cap20-20261019-2151-build_tower-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"build_tower"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["semantic-eef-classify-cap20-20261019-2039-classify_objects-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-classify_objects-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects"},{"capability":"Open","completed":2,"expected":2,"run_ids":["semantic-eef-classify-objects-by-language-cap20-20261019-2151-classify_objects_by_language-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-classify_objects_by_language-standard-s0-scene1"],"score":0.7,"success_rate":0.5,"task":"classify_objects_by_language"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["semantic-eef-cover-blocks-cap20-20261019-2151-cover_blocks-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-cover_blocks-standard-s0-scene1"],"score":0.075,"success_rate":0.0,"task":"cover_blocks"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-coin-cap20-20261019-1955-deposit_coin-standard-s0-scene0"],"score":0.2,"success_rate":0.0,"task":"deposit_coin"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["semantic-eef-fasten-screws-cap20-20261019-2151-fasten_screws-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fasten_screws-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"fasten_screws"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-fill-egg-holder-cap20-20261019-2151-fill_egg_holder-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"fill_egg_holder"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-fill-pen-holder-cap20-20261019-2151-fill_pen_holder-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"fill_pen_holder"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["semantic-eef-fold-clothes-cap20-20261019-2151-fold_clothes-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-fold_clothes-standard-s0-scene0"],"score":0.6,"success_rate":0.5,"task":"fold_clothes"},{"capability":"Open","completed":2,"expected":2,"run_ids":["semantic-eef-general-pickup-cap20-20261019-2151-general_pickup-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-general_pickup-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"general_pickup"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-hang-mugs-cap20-20261019-2039-hang_mugs-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"hang_mugs"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["semantic-eef-imitate-sorting-sequence-cap20-20261019-2151-imitate_sorting_sequence-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-imitate_sorting_sequence-standard-s0-scene1"],"score":0.75,"success_rate":0.5,"task":"imitate_sorting_sequence"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-insert-key-cap20-20261019-2151-insert_key-standard-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"insert_key"},{"capability":"Precision","completed":1,"expected":1,"run_ids":["semantic-eef-insert-tubes-cap20-20261019-2039-insert_tubes-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"insert_tubes"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-make-kong-cap20-20261019-2151-make_kong-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_kong"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-make-toast-cap20-20261019-2151-make_toast-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"make_toast"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["semantic-eef-match-and-pick-from-conveyor-cap20-20261019-2151-match_and_pick_from_conveyor-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-match_and_pick_from_conveyor-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"match_and_pick_from_conveyor"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-organize-table-cap20-20261019-2151-organize_table-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"organize_table"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["semantic-eef-pack-cap20-20261019-1955-pack_objects_into_box-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pack_objects_into_box-standard-s0-scene0"],"score":0.55,"success_rate":0.5,"task":"pack_objects_into_box"},{"capability":"Open","completed":2,"expected":2,"run_ids":["semantic-eef-pick-from-conveyor-by-image-cap20-20261019-2151-pick_from_conveyor_by_image-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pick_from_conveyor_by_image-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"pick_from_conveyor_by_image"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["semantic-eef-play-xylophone-cap20-20261019-2151-play_Xylophone-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-play_Xylophone-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"play_Xylophone"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-play-stacking-toy-cap20-20261019-2151-play_stacking_toy-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_stacking_toy"},{"capability":"Long-Horizon","completed":1,"expected":1,"run_ids":["semantic-eef-play-tic-tac-toe-cap20-20261019-2151-play_tic_tac_toe-standard-s0-scene0"],"score":0.1,"success_rate":0.0,"task":"play_tic_tac_toe"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["semantic-eef-plug-charger-cap20-20261019-2123-plug_in_charger-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-plug_in_charger-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"plug_in_charger"},{"capability":"Precision","completed":2,"expected":2,"run_ids":["semantic-eef-pour-cap20-20261019-1955-pour_balls_into_vase-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-pour_balls_into_vase-standard-s0-scene1"],"score":0.5,"success_rate":0.5,"task":"pour_balls_into_vase"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-pour-by-language-cap20-20261019-2151-pour_by_language-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_by_language"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-pour-liquid-into-cup-cap20-20261019-2151-pour_liquid_into_cup-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"pour_liquid_into_cup"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["semantic-eef-press-by-number-cap20-20261019-2151-press_by_number-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-press_by_number-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"press_by_number"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["semantic-eef-push-t-cap20-retry1-20261019-2247-push_T-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-push_T-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"push_T"},{"capability":"Long-Horizon","completed":2,"expected":2,"run_ids":["semantic-eef-put-bottles-into-dustbin-cap20-20261019-2151-put_bottles_into_dustbin-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-put_bottles_into_dustbin-standard-s0-scene1"],"score":0.325,"success_rate":0.0,"task":"put_bottles_into_dustbin"},{"capability":"Open","completed":2,"expected":2,"run_ids":["semantic-eef-solve-equation-cap20-20261019-2151-solve_equation-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-solve_equation-standard-s0-scene1"],"score":1.0,"success_rate":1.0,"task":"solve_equation"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["semantic-eef-sort-nesting-dolls-by-size-cap20-20261019-2151-sort_nesting_dolls_by_size-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-sort_nesting_dolls_by_size-standard-s0-scene0"],"score":0.5,"success_rate":0.5,"task":"sort_nesting_dolls_by_size"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-stack-blocks-cap20-20261019-2151-stack_blocks-random-s0-scene0"],"score":0.15,"success_rate":0.0,"task":"stack_blocks"},{"capability":"Open","completed":2,"expected":2,"run_ids":["semantic-eef-stack-blocks-by-language-cap20-20261019-2151-stack_blocks_by_language-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_blocks_by_language-standard-s0-scene1"],"score":0.6,"success_rate":0.5,"task":"stack_blocks_by_language"},{"capability":"Generalization","completed":2,"expected":2,"run_ids":["semantic-eef-stack-bowls-cap20-20261019-2123-stack_bowls-random-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-stack_bowls-standard-s0-scene0"],"score":1.0,"success_rate":1.0,"task":"stack_bowls"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-store-laptop-and-headphones-cap20-20261019-2151-store_laptop_and_headphones-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_laptop_and_headphones"},{"capability":"Open","completed":1,"expected":1,"run_ids":["semantic-eef-store-tools-in-toolbox-cap20-20261019-2151-store_tools_in_toolbox-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"store_tools_in_toolbox"},{"capability":"Memory","completed":2,"expected":2,"run_ids":["semantic-eef-swap-t-cap20-20261019-2151-swap_T-standard-s0-scene0","semantic-eef-devset69-cap20-20261020-restart3-swap_T-standard-s0-scene1"],"score":0.0,"success_rate":0.0,"task":"swap_T"},{"capability":"Memory","completed":1,"expected":1,"run_ids":["semantic-eef-swap-blocks-cap20-20261019-2151-swap_blocks-standard-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"swap_blocks"},{"capability":"Generalization","completed":1,"expected":1,"run_ids":["semantic-eef-sweep-blocks-cap20-20261019-2151-sweep_blocks-random-s0-scene0"],"score":0.0,"success_rate":0.0,"task":"sweep_blocks"}]}},"experiment_id":"07a9a47304c314802f805a3f7871cc3aa46ac8532bb3d72501ae7727bd60b2c1","name":"semantic-eef","selection_id":"semantic-eef-cap20-20261019"}],"plan_version":"2026-10-17","plans":{"P50_111":{"cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"expected":111,"label":"P50_111","plan_id":"P50_111","selection_rule":"相同≤50资格，23个合格任务全部测4次，其余1次。排名只作解释，不截断、不使用预算优化器。","task_count":42},"first_round":{"cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"expected":42,"label":"首轮42","plan_id":"first_round","task_count":42},"spiky2_65":{"cases":[{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"}],"description":"23 spiky tasks twice, 19 other tasks once; includes the first round. Ordinary repeats use standard scene0/1; Generalization repeats use random/standard scene0. Seed zero; unchanged official task/capability averaging.","expected":65,"label":"Spiky-2（65例）","plan_id":"spiky2_65","source_proposal_sha256":"32de09a8c9fae7dc1f4b7d0299e3e008da1be26837bc95e9ea9504f206d722e6","task_count":42}},"schema_version":"robodojo-api-v1","score_scale":"0..1","snapshot_id":"6de891ddca6174e456e977647b6e9fb30ee5587cc8e74659138d072d01a66a0e"}
