IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Completed task success rate
100.0%
50 of 50
Control horizon
280
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
5m 27s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the salad dressing and place it in the basket
BDDL language
pick the salad dressing and place it in the basket
Problem
libero_floor_manipulation
Objects
alphabet_soup_1, basket_1, cream_cheese_1, ketchup_1, milk_1, salad_dressing_1, tomato_sauce_1
Fixtures
floor
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates
(on salad_dressing_1 floor_target_object_region)
(on ketchup_1 floor_other_object_region_0)
(on alphabet_soup_1 floor_other_object_region_1)
(on cream_cheese_1 floor_other_object_region_2)
(on milk_1 floor_other_object_region_3)
(on tomato_sauce_1 floor_other_object_region_4)
(on basket_1 floor_bin_region)

Open exact BDDL definition

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.

  1. salad dressing 1 is in basket 1 contain region

    (in salad_dressing_1 basket_1_contain_region)
Exact parsed BDDL goal state
(in salad_dressing_1 basket_1_contain_region)

Selected rollout

LIBERO-Object · Task 002 · Episode 1

Success
Agent view observation.images.image
Eye in hand observation.images.image2
Videos are not loaded yet.

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 0 105 105 KB
2 Success 1001 2 104 104 KB
3 Success 1002 4 104 103 KB
4 Success 1003 6 109 108 KB
5 Success 1004 8 104 102 KB
6 Success 1005 10 107 107 KB
7 Success 1006 12 104 103 KB
8 Success 1007 14 109 108 KB
9 Success 1008 16 109 108 KB
10 Success 1009 18 112 109 KB
11 Success 1010 20 102 103 KB
12 Success 1011 22 102 105 KB
13 Success 1012 24 111 111 KB
14 Success 1013 26 117 115 KB
15 Success 1014 28 116 116 KB
16 Success 1015 30 103 100 KB
17 Success 1016 32 123 117 KB
18 Success 1017 34 105 102 KB
19 Success 1018 36 103 103 KB
20 Success 1019 38 107 107 KB
21 Success 1020 40 110 111 KB
22 Success 1021 42 107 106 KB
23 Success 1022 44 105 106 KB
24 Success 1023 46 113 111 KB
25 Success 1024 48 114 111 KB
26 Success 1025 0 104 104 KB
27 Success 1026 2 105 106 KB
28 Success 1027 4 101 101 KB
29 Success 1028 6 114 111 KB
30 Success 1029 8 105 106 KB
31 Success 1030 10 107 108 KB
32 Success 1031 12 105 104 KB
33 Success 1032 14 109 108 KB
34 Success 1033 16 109 107 KB
35 Success 1034 18 115 109 KB
36 Success 1035 20 106 106 KB
37 Success 1036 22 111 110 KB
38 Success 1037 24 106 105 KB
39 Success 1038 26 105 104 KB
40 Success 1039 28 114 112 KB
41 Success 1040 30 103 102 KB
42 Success 1041 32 119 114 KB
43 Success 1042 34 104 101 KB
44 Success 1043 36 103 102 KB
45 Success 1044 38 105 105 KB
46 Success 1045 40 105 104 KB
47 Success 1046 42 107 107 KB
48 Success 1047 44 108 106 KB
49 Success 1048 46 112 111 KB
50 Success 1049 48 114 108 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 2:33 AM UTC
Manifest SHA-256
884349fa29…fc3c1a3e
Aggregate SHA-256
a6eb67c9bc…e07d5fe5
Episode index SHA-256
cc0b7f2159…d3bb035b
Validation SHA-256
e3c538d2c3…3b4f949c
Artifact inventory SHA-256
44b7834120…83fd9d32