Paper protocol Task 007 Validated task
turn on the stove
- Completed task success rate
- 96.0%
- 48 of 50
- Control horizon
- 300
- Maximum steps
- Camera videos
- 100
- Two per rollout
- Evaluation time
- 5m 3s
- Task process wall time
Canonical catalog
Task definition
- Model instruction
- turn on the stove
- BDDL language
- turn on the stove
- Problem
- libero_tabletop_manipulation
- Objects
- akita_black_bowl_1, cream_cheese_1, plate_1, wine_bottle_1
- Fixtures
- flat_stove_1, main_table, wine_rack_1, wooden_cabinet_1
- Initial-state predicates
- 7
- Fixed init states
- 50
Exact initial-state predicates
(on wine_bottle_1 main_table_wine_bottle_region)
(on akita_black_bowl_1 main_table_akita_black_bowl_region)
(on plate_1 main_table_plate_region)
(on cream_cheese_1 main_table_cream_cheese_region)
(on wooden_cabinet_1 main_table_cabinet_region)
(on flat_stove_1 main_table_stove_region)
(on wine_rack_1 main_table_wine_rack_region) Simulator truth
Completion criteria
LIBERO checks these BDDL goal predicates after every action. All conditions must be true simultaneously in the same simulator step for the rollout to succeed.
-
flat stove 1 is turned on
(turnon flat_stove_1)
Exact parsed BDDL goal state
(turnon flat_stove_1) Selected rollout
LIBERO-Goal · Task 007 · Episode 1
Evidence browser
All rollouts
Select one episode to mount only its two camera streams in the player.
| Episode | Outcome | Seed | Init state | Steps | Video | Select |
|---|---|---|---|---|---|---|
| 1 | Success | 1000 | 0 | 87 | 61 KB | |
| 2 | Success | 1001 | 2 | 94 | 66 KB | |
| 3 | Success | 1002 | 4 | 84 | 56 KB | |
| 4 | Success | 1003 | 6 | 81 | 64 KB | |
| 5 | Success | 1004 | 8 | 95 | 69 KB | |
| 6 | Success | 1005 | 10 | 92 | 67 KB | |
| 7 | Success | 1006 | 12 | 85 | 62 KB | |
| 8 | Success | 1007 | 14 | 84 | 61 KB | |
| 9 | Success | 1008 | 16 | 87 | 63 KB | |
| 10 | Success | 1009 | 18 | 86 | 63 KB | |
| 11 | Success | 1010 | 20 | 85 | 61 KB | |
| 12 | Success | 1011 | 22 | 70 | 53 KB | |
| 13 | Success | 1012 | 24 | 91 | 65 KB | |
| 14 | Success | 1013 | 26 | 84 | 59 KB | |
| 15 | Success | 1014 | 28 | 89 | 62 KB | |
| 16 | Success | 1015 | 30 | 81 | 58 KB | |
| 17 | Success | 1016 | 32 | 83 | 60 KB | |
| 18 | Success | 1017 | 34 | 81 | 59 KB | |
| 19 | Success | 1018 | 36 | 78 | 57 KB | |
| 20 | Success | 1019 | 38 | 82 | 61 KB | |
| 21 | Success | 1020 | 40 | 78 | 59 KB | |
| 22 | Failure | 1021 | 42 | 300 | 87 KB | |
| 23 | Success | 1022 | 43 | 87 | 61 KB | |
| 24 | Success | 1023 | 45 | 93 | 65 KB | |
| 25 | Success | 1024 | 47 | 80 | 60 KB | |
| 26 | Success | 1025 | 49 | 77 | 60 KB | |
| 27 | Success | 1026 | 1 | 110 | 79 KB | |
| 28 | Success | 1027 | 3 | 80 | 60 KB | |
| 29 | Success | 1028 | 5 | 97 | 67 KB | |
| 30 | Success | 1029 | 7 | 89 | 62 KB | |
| 31 | Success | 1030 | 9 | 82 | 55 KB | |
| 32 | Success | 1031 | 11 | 80 | 58 KB | |
| 33 | Success | 1032 | 13 | 82 | 60 KB | |
| 34 | Success | 1033 | 15 | 77 | 58 KB | |
| 35 | Success | 1034 | 17 | 82 | 58 KB | |
| 36 | Success | 1035 | 19 | 84 | 62 KB | |
| 37 | Success | 1036 | 21 | 88 | 61 KB | |
| 38 | Success | 1037 | 23 | 84 | 60 KB | |
| 39 | Success | 1038 | 25 | 89 | 65 KB | |
| 40 | Success | 1039 | 27 | 86 | 61 KB | |
| 41 | Success | 1040 | 29 | 68 | 58 KB | |
| 42 | Success | 1041 | 31 | 78 | 57 KB | |
| 43 | Success | 1042 | 33 | 86 | 60 KB | |
| 44 | Success | 1043 | 35 | 78 | 59 KB | |
| 45 | Success | 1044 | 37 | 75 | 57 KB | |
| 46 | Success | 1045 | 39 | 81 | 60 KB | |
| 47 | Success | 1046 | 41 | 90 | 61 KB | |
| 48 | Success | 1047 | 43 | 88 | 60 KB | |
| 49 | Success | 1048 | 45 | 88 | 60 KB | |
| 50 | Failure | 1049 | 47 | 300 | 86 KB |
No matching rollouts
Change the outcome filter or clear the search field.
Integrity
Task attestation
- Status
- complete
- Completed
- Aug 16, 2026, 2:02 AM UTC
- Manifest SHA-256
- 694101f309…cf73f71c
- Aggregate SHA-256
- 4281264c25…25eeae40
- Episode index SHA-256
- fbddc6909a…74b85eca
- Validation SHA-256
- f0409bcc90…5dec6653
- Artifact inventory SHA-256
- f398e5a4fb…976b1e53