{"round_selections":[{"comparison":{"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"protocol":{"max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20","score_scale":"0..1"}},"id":"medium-cap20-rounds4-v2","round_plan_sha256":"f6dff38f9e7990eb0cedd4a8b764a2bbd6cbb16dcf4d95dcbd6b8c659d811a00","rounds":[{"expected_episodes":[{"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"}],"label":"R1: seed0; non-random tasks scene0; random-capable tasks random scene0","round":1},{"expected_episodes":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"build_tower","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":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"fill_pen_holder","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":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"organize_table","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":"Long-Horizon","scene":1,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":1,"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":1,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","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":"Generalization","scene":0,"seed":0,"task":"stack_blocks","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":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"standard"}],"label":"R2: seed0; non-random tasks scene1; random-capable tasks standard scene0","round":2},{"expected_episodes":[{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":2,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":2,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sweep_blocks","variant":"random"}],"label":"R3: seed0; non-random tasks scene2; random-capable tasks random scene1","round":3},{"expected_episodes":[{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"hang_mugs","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"make_toast","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sweep_blocks","variant":"standard"}],"label":"R4: seed0; non-random tasks scene3; random-capable tasks standard scene1","round":4},{"expected_episodes":[{"capability":"Open","scene":4,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":4,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":4,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":4,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":55,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":4,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":4,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":4,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":4,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":4,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":4,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":4,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"sweep_blocks","variant":"random"}],"label":"R5: seed0; non-random tasks scene4; Generalization random scene2; imitate_sorting_sequence actual scene55","round":5},{"expected_episodes":[{"capability":"Generalization","scene":2,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"hang_mugs","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"sweep_blocks","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"make_toast","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"stack_blocks","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R6: seed0; non-random tasks scene5; Generalization standard scene2","round":6},{"expected_episodes":[{"capability":"Generalization","scene":3,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"sweep_blocks","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Precision","scene":6,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R7: seed0; non-random tasks scene6; Generalization random scene3","round":7},{"expected_episodes":[{"capability":"Generalization","scene":3,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"hang_mugs","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"sweep_blocks","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"make_toast","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"stack_blocks","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R8: seed0; non-random tasks scene7; Generalization standard scene3","round":8}],"schema_version":"l3-declared-round-selection-v1","source_harness_bindings":[{"harness_kind":"historical","harness_sha256":"79f2a582c840993b1ddebc95d9fcf60999c84cf552f7dd5210a0c092a3b50c3a","protocol_id":"persistent-cap20-medium-historical-v1","selection_id":"medium-cap20-alternating4-v1"},{"harness_kind":"historical","harness_sha256":"79f2a582c840993b1ddebc95d9fcf60999c84cf552f7dd5210a0c092a3b50c3a","protocol_id":"persistent-cap20-medium-historical-v1","selection_id":"medium-cap20-evidence216-v1"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene4-medium-20261014","selection_id":"thunlp-cap20-scene4-medium-20261014"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene4-medium-restart01-20261014","selection_id":"thunlp-cap20-scene4-medium-restart01-20261014"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene4-medium-restart02-20261015","selection_id":"thunlp-cap20-scene4-medium-restart02-20261015"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene4-medium-restart03-20261015","selection_id":"thunlp-cap20-scene4-medium-restart03-20261015"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene4-medium-restart07-20261015","selection_id":"thunlp-cap20-scene4-medium-restart07-20261015"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene5-genstandard2-medium-20261015","selection_id":"thunlp-cap20-scene5-genstandard2-medium-20261015"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","selection_id":"thunlp-cap20-scene5-genstandard2-medium-queued01-20261015"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","selection_id":"thunlp-cap20-scene5-genstandard2-medium-queued02-20261015"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"l3-medium-r7-mixed42-20261016","selection_id":"l3-medium-r7-mixed42-20261016"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"l3-medium-r8-mixed42-20261016","selection_id":"l3-medium-r8-mixed42-20261016"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"thunlp-cap20-scene5-genstandard2-medium-final01-20261016","selection_id":"thunlp-cap20-scene5-genstandard2-medium-final01-20261016"},{"harness_kind":"native","harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","protocol_id":"l3-medium-r5-scene55-substitute-20261017","selection_id":"l3-medium-r5-scene55-substitute-20261017"}],"source_selection_ids":["medium-cap20-alternating4-v1","medium-cap20-evidence216-v1","thunlp-cap20-scene4-medium-restart01-20261014","thunlp-cap20-scene4-medium-restart03-20261015","thunlp-cap20-scene4-medium-20261014","thunlp-cap20-scene4-medium-restart02-20261015","thunlp-cap20-scene4-medium-restart07-20261015","thunlp-cap20-scene5-genstandard2-medium-20261015","thunlp-cap20-scene5-genstandard2-medium-queued01-20261015","thunlp-cap20-scene5-genstandard2-medium-queued02-20261015","l3-medium-r7-mixed42-20261016","l3-medium-r8-mixed42-20261016","thunlp-cap20-scene5-genstandard2-medium-final01-20261016","l3-medium-r5-scene55-substitute-20261017"],"title":"Persistent cap20 medium · 8 declared rounds"},{"harness_sha256":"ea220fcf7f735a22e207a7b2905ed27b1cc3375c9abd78fb965e88e575b205c3","id":"low-cap20-rounds8-infra-v2","round_plan_sha256":"ad43784cc214fd021cc52ef4fccb502da5e88b8615591453de7ca5e6696963c1","rounds":[{"expected_episodes":[{"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"}],"label":"R1: seed0; non-random tasks scene0; random-capable tasks random scene0","round":1},{"expected_episodes":[{"capability":"Open","scene":1,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"build_tower","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":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"fill_pen_holder","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":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":1,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":1,"seed":0,"task":"organize_table","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":"Long-Horizon","scene":1,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":1,"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":1,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","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":"Generalization","scene":0,"seed":0,"task":"stack_blocks","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":"standard"},{"capability":"Open","scene":1,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":1,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"standard"}],"label":"R2: seed0; non-random tasks scene1; random-capable tasks standard scene0","round":2},{"expected_episodes":[{"capability":"Open","scene":2,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":2,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Open","scene":2,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Memory","scene":2,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Memory","scene":2,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Open","scene":2,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":2,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Memory","scene":2,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"random"},{"capability":"Long-Horizon","scene":2,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":2,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Open","scene":2,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":1,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Open","scene":2,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":2,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sweep_blocks","variant":"random"}],"label":"R3: seed0; non-random tasks scene2; random-capable tasks random scene1","round":3},{"expected_episodes":[{"capability":"Open","scene":3,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"hang_mugs","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"make_toast","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":3,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"pour_by_language","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Long-Horizon","scene":3,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_blocks","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},{"capability":"Open","scene":3,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":3,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Generalization","scene":1,"seed":0,"task":"sweep_blocks","variant":"standard"}],"label":"R4: seed0; non-random tasks scene3; random-capable tasks standard scene1","round":4},{"expected_episodes":[{"capability":"Generalization","scene":2,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"sweep_blocks","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Generalization","scene":2,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Precision","scene":4,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":4,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":4,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":4,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":4,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":4,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":4,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":4,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":55,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":4,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R5: seed0; non-random tasks scene4; random-capable tasks random scene2; imitate_sorting_sequence uses authorized scene55 in place of scene4","round":5},{"expected_episodes":[{"capability":"Generalization","scene":2,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"hang_mugs","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"sweep_blocks","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"make_toast","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},{"capability":"Generalization","scene":2,"seed":0,"task":"stack_blocks","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":5,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":5,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":5,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":5,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R6: seed0; non-random tasks scene5; random-capable tasks standard scene2","round":6},{"expected_episodes":[{"capability":"Generalization","scene":3,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"sweep_blocks","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Generalization","scene":3,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Precision","scene":6,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":6,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":6,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":6,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":6,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R7: seed0; non-random tasks scene6; random-capable tasks random scene3","round":7},{"expected_episodes":[{"capability":"Generalization","scene":3,"seed":0,"task":"stack_bowls","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"push_T","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"pack_objects_into_box","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"fold_clothes","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"hang_mugs","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"sweep_blocks","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"pour_liquid_into_cup","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"make_toast","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"arrange_largest_number","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"store_laptop_and_headphones","variant":"standard"},{"capability":"Generalization","scene":3,"seed":0,"task":"stack_blocks","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":7,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":7,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":7,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":7,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R8: seed0; non-random tasks scene7; random-capable tasks standard scene3","round":8}],"schema_version":"l3-native-round-selection-v1","source_protocol_bindings":[{"protocol_id":"l3-low-mixed42-20261012","selection_id":"l3-low-mixed42-20261012"},{"protocol_id":"l3-low-r2-mixed42-20261013","selection_id":"l3-low-r2-mixed42-20261013"},{"protocol_id":"l3-low-r3-mixed42-20261013","selection_id":"l3-low-r3-mixed42-20261013"},{"protocol_id":"l3-low-r4-mixed42-20261013","selection_id":"l3-low-r4-mixed42-20261013"},{"protocol_id":"l3-low-r2-infra72retry1-20261014","selection_id":"l3-low-r2-infra72retry1-20261014"},{"protocol_id":"l3-low-r3-infra72retry1-20261014","selection_id":"l3-low-r3-infra72retry1-20261014"},{"protocol_id":"l3-low-r4-infra72retry1-20261014","selection_id":"l3-low-r4-infra72retry1-20261014"},{"protocol_id":"l3-low-r5-mixed42-20261014","selection_id":"l3-low-r5-mixed42-20261014"},{"protocol_id":"l3-low-r6-mixed42-20261014","selection_id":"l3-low-r6-mixed42-20261014"},{"protocol_id":"l3-low-r7-mixed42-20261014","selection_id":"l3-low-r7-mixed42-20261014"},{"protocol_id":"l3-low-r8-mixed42-20261014","selection_id":"l3-low-r8-mixed42-20261014"},{"protocol_id":"l3-low-r5-mixed42-20261014-initretry1","selection_id":"l3-low-r5-mixed42-20261014-initretry1"},{"protocol_id":"l3-low-r6-mixed42-20261014-initretry1","selection_id":"l3-low-r6-mixed42-20261014-initretry1"},{"protocol_id":"l3-low-r7-mixed42-20261014-initretry1","selection_id":"l3-low-r7-mixed42-20261014-initretry1"},{"protocol_id":"l3-low-r8-mixed42-20261014-initretry1","selection_id":"l3-low-r8-mixed42-20261014-initretry1"},{"protocol_id":"l3-low-r5-mixed42-20261014-retry33a1","selection_id":"l3-low-r5-mixed42-20261014-retry33a1"},{"protocol_id":"l3-low-r5-scene55-substitute-20261015","selection_id":"l3-low-r5-scene55-substitute-20261015"}],"source_selection_ids":["l3-low-mixed42-20261012","l3-low-r2-mixed42-20261013","l3-low-r3-mixed42-20261013","l3-low-r4-mixed42-20261013","l3-low-r2-infra72retry1-20261014","l3-low-r3-infra72retry1-20261014","l3-low-r4-infra72retry1-20261014","l3-low-r5-mixed42-20261014","l3-low-r6-mixed42-20261014","l3-low-r7-mixed42-20261014","l3-low-r8-mixed42-20261014","l3-low-r5-mixed42-20261014-initretry1","l3-low-r6-mixed42-20261014-initretry1","l3-low-r7-mixed42-20261014-initretry1","l3-low-r8-mixed42-20261014-initretry1","l3-low-r5-mixed42-20261014-retry33a1","l3-low-r5-scene55-substitute-20261015"],"title":"persistent-cap20 low: eight explicit variant-local scene rounds"},{"harness_sha256":"8021b8f45d0a773a0563fc100f6c3405c700a76b1e934682d4f3b28379efc890","id":"persistent-nocap-medium-mixed42-v1","rounds":[{"expected_episodes":[{"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"}],"label":"R1: 30 standard + 12 random Generalization; seed0 scene0","round":1}],"schema_version":"l3-round-selection-v1","source_report_sha256":"653c48e941e2e98df70f06783478053743f4893e702c43efe0d190d71024ba36","source_selection_ids":["persistent-nocap-medium-full54-v1"],"title":"persistent-nocap medium: R1, 30 standard + 12 random Generalization; seed0 scene0"},{"harness_sha256":"18230dfa77ce6dec6ac6d12de65e0b0371a5dda329b512345d1c9edb6b5ca721","id":"persistent-cap20-rerun","round_plan_sha256":"1d128224cfe0d103e13684029742742b05bb4d11c57faf33a8803a0c9f1bbaec","rounds":[{"expected_episodes":[{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R1: 30 standard + 12 random Generalization; seed0 scene0","round":1}],"schema_version":"l3-native-round-selection-v1","source_protocol_bindings":[{"protocol_id":"thunlp-persistent-cap20-medium-local13-20261013","selection_id":"thunlp-persistent-cap20-medium-local13-20261013"},{"protocol_id":"thunlp-persistent-cap20-medium-local42-20261012","selection_id":"thunlp-persistent-cap20-medium-local42-20261012"},{"protocol_id":"thunlp-persistent-cap20-medium-retry9-20261013","selection_id":"thunlp-persistent-cap20-medium-retry9-20261013"},{"protocol_id":"thunlp-persistent-cap20-medium-smoke-20261012","selection_id":"thunlp-persistent-cap20-medium-smoke-20261012"}],"source_selection_ids":["thunlp-persistent-cap20-medium-local13-20261013","thunlp-persistent-cap20-medium-local42-20261012","thunlp-persistent-cap20-medium-retry9-20261013","thunlp-persistent-cap20-medium-smoke-20261012"],"title":"persistent-cap20-rerun"},{"harness_sha256":"8c43b32a9126de46426131964ae4bcf2d33046481236bc2413ffbdde1190a6bc","id":"persistent-nocap-rerun","round_plan_sha256":"1d128224cfe0d103e13684029742742b05bb4d11c57faf33a8803a0c9f1bbaec","rounds":[{"expected_episodes":[{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R1: 30 standard + 12 random Generalization; seed0 scene0","round":1}],"schema_version":"l3-native-round-selection-v1","source_protocol_bindings":[{"protocol_id":"thunlp-full-ik3-retry02-20261014","selection_id":"thunlp-full-ik3-retry02-20261014"},{"protocol_id":"thunlp-full-ik42-medium-20261013","selection_id":"thunlp-full-ik42-medium-20261013"}],"source_selection_ids":["thunlp-full-ik3-retry02-20261014","thunlp-full-ik42-medium-20261013"],"title":"persistent-nocap-rerun"},{"harness_sha256":"cf83b0681740016e78fbb5603efab550cff47eb73d9b70b2a4a51e4939a3296e","id":"l3-o1-r1-mixed42-20261016","round_plan_sha256":"dfc406cb664b8a36fd243447113097388991b9cff1e1f34cd8461552100ada7b","rounds":[{"expected_episodes":[{"capability":"Generalization","scene":0,"seed":0,"task":"stack_bowls","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"push_T","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pack_objects_into_box","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"fold_clothes","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"hang_mugs","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sweep_blocks","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"pour_liquid_into_cup","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"make_toast","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"sort_nesting_dolls_by_size","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"store_laptop_and_headphones","variant":"random"},{"capability":"Generalization","scene":0,"seed":0,"task":"stack_blocks","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"fasten_screws","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"plug_in_charger","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_tubes","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"pour_balls_into_vase","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"play_Xylophone","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"deposit_coin","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"insert_key","variant":"standard"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"put_bottles_into_dustbin","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_pen_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"classify_objects","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_tic_tac_toe","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"fill_egg_holder","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"organize_table","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"make_kong","variant":"standard"},{"capability":"Long-Horizon","scene":0,"seed":0,"task":"play_stacking_toy","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"cover_blocks","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"match_and_pick_from_conveyor","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_blocks","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"swap_T","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"press_by_number","variant":"standard"},{"capability":"Memory","scene":0,"seed":0,"task":"imitate_sorting_sequence","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"align_blocks","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"general_pickup","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"stack_blocks_by_language","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"solve_equation","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"classify_objects_by_language","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pick_from_conveyor_by_image","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"store_tools_in_toolbox","variant":"standard"},{"capability":"Open","scene":0,"seed":0,"task":"pour_by_language","variant":"standard"}],"label":"R1 · seed0 / scene0 · mixed42","round":1}],"schema_version":"l3-native-round-selection-v1","source_protocol_bindings":[{"protocol_id":"l3-o1-precision4-20261016-v1","selection_id":"l3-o1-precision4-20261016-v1"},{"protocol_id":"l3-o1-r1-mixed42-20261016","selection_id":"l3-o1-r1-mixed42-20261016"},{"protocol_id":"l3-o1-r1-mixed42-retry01-20261017","selection_id":"l3-o1-r1-mixed42-retry01-20261017"}],"source_selection_ids":["l3-o1-precision4-20261016-v1","l3-o1-r1-mixed42-20261016","l3-o1-r1-mixed42-retry01-20261017"],"title":"persistent-cap20-o1 · medium · R1"},{"comparison":{"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"protocol":{"max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23","score_scale":"0..1"}},"id":"l3-o23-full-ik42-medium-r1-20261017","round_plan_sha256":"563934356448dcef8ede7c55ddc26cebcc9f71352bbf42e76313fc5701d1601f","rounds":[{"expected_episodes":[{"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"}],"label":"O23 first round","round":1}],"schema_version":"l3-declared-round-selection-v1","source_harness_bindings":[{"harness_kind":"native","harness_sha256":"114f9d101cc64fa2683d043cb777042a1d7927b58a1b23aadd7d31bbad0f0ab8","protocol_id":"l3-o23-precision4-20261017-v1","selection_id":"l3-o23-precision4-20261017-v1"},{"harness_kind":"native","harness_sha256":"9a24041315c572464b0f2e77c1f06d5e2f1a46936cfa14b064c26a53010b7b28","protocol_id":"l3-o23-full-ik42-medium-r1-20261017","selection_id":"l3-o23-full-ik42-medium-r1-20261017"}],"source_selection_ids":["l3-o23-precision4-20261017-v1","l3-o23-full-ik42-medium-r1-20261017"],"title":"O23 compact · medium · R1"},{"comparison":{"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"protocol":{"max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o456-clear","score_scale":"0..1"}},"id":"l3-o456-clear-20261019","round_plan_sha256":"7e7456e95fd721a0b5066a1108b294c69d8cacec6e4384a1058452f241b7274c","rounds":[{"expected_episodes":[{"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"}],"label":"R1 · 42 tasks · seed0 / scene0","round":1}],"schema_version":"l3-declared-round-selection-v1","source_harness_bindings":[{"harness_kind":"native","harness_sha256":"f45248dab042c86f391c198f3ed9274791b330fad9f4ccec7b979604926e0f1f","protocol_id":"l3-o456-clear-generalization12-20261019-v1","selection_id":"l3-o456-clear-generalization12-20261019-v1"},{"harness_kind":"native","harness_sha256":"f45248dab042c86f391c198f3ed9274791b330fad9f4ccec7b979604926e0f1f","protocol_id":"l3-o456-clear-precision4-20261018-v1","selection_id":"l3-o456-clear-precision4-20261018-v1"},{"harness_kind":"native","harness_sha256":"f45248dab042c86f391c198f3ed9274791b330fad9f4ccec7b979604926e0f1f","protocol_id":"l3-o456-clear-precision8-completion-20261019-v1","selection_id":"l3-o456-clear-precision8-completion-20261019-v1"},{"harness_kind":"native","harness_sha256":"1d2d45ef7c64b5703a1bbff809d7b9c7cc56f30400beab5d9c8f6ca96f3ef8c1","protocol_id":"l3-o456-clear-olm22-medium-r1-20261019","selection_id":"l3-o456-clear-olm22-medium-r1-20261019"}],"source_selection_ids":["l3-o456-clear-generalization12-20261019-v1","l3-o456-clear-precision4-20261018-v1","l3-o456-clear-precision8-completion-20261019-v1","l3-o456-clear-olm22-medium-r1-20261019"],"title":"persistent-cap20-o456-clear"},{"comparison":{"model":{"client_version":"0.153.4","name":"gpt-6-astra","thinking_effort":"medium"},"protocol":{"max_decisions":100,"native_control_cap":20,"profile":"persistent-cap20-o23456-pure","score_scale":"0..1"}},"id":"l3-o23456-pure-20261020","round_plan_sha256":"752a4854322cab03ea6dad119fcb2d2379fa5ed1b66db248cdeee6977c0bf9ea","rounds":[{"expected_episodes":[{"capability":"Generalization","scene":0,"seed":0,"task":"arrange_largest_number","variant":"random"},{"capability":"Precision","scene":0,"seed":0,"task":"build_tower","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":"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":"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":"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"}],"label":"R1 · Precision 8 + Generalization 12 · seed0 / scene0","round":1}],"schema_version":"l3-declared-round-selection-v1","source_harness_bindings":[{"harness_kind":"native","harness_sha256":"6c1fadf8427d40ed9fab74137629537fbd292b8b95e180403a1225274082fc38","protocol_id":"l3-o23456-pure-precision8-20261020-v1","selection_id":"l3-o23456-pure-precision8-20261020-v1"},{"harness_kind":"native","harness_sha256":"6c1fadf8427d40ed9fab74137629537fbd292b8b95e180403a1225274082fc38","protocol_id":"l3-o23456-pure-generalization12-20261020-v1","selection_id":"l3-o23456-pure-generalization12-20261020-v1"}],"source_selection_ids":["l3-o23456-pure-precision8-20261020-v1","l3-o23456-pure-generalization12-20261020-v1"],"title":"persistent-cap20-o23456-pure"}],"schema_version":"robodojo-api-v1","snapshot_id":"6de891ddca6174e456e977647b6e9fb30ee5587cc8e74659138d072d01a66a0e"}
