yzzhao commited on
Commit
414d668
·
verified ·
1 Parent(s): 5862de5

Publish codex SIMPLE seed-0 evaluation evidence

Browse files
Files changed (5) hide show
  1. data.json +4 -4
  2. manifest.json +3 -3
  3. publication-manifest.json +6 -6
  4. summary.json +2 -2
  5. task-index.json +1 -1
data.json CHANGED
@@ -6,7 +6,7 @@
6
  "benchmark_complete": false,
7
  "edition": "codex-simple-astra-high-seed0",
8
  "created_at": "2026-10-09T00:09:42.989838+00:00",
9
- "updated_at": "2026-10-10T01:07:02.288183+00:00",
10
  "model": "gpt-6-astra",
11
  "effort": "high",
12
  "seed": 0,
@@ -129,8 +129,8 @@
129
  "new_evaluations": 7,
130
  "progress": {
131
  "finished": 79,
132
- "running": 2,
133
- "queued": 3,
134
  "needs_review": 0,
135
  "interrupted": 0,
136
  "native_successes": 51,
@@ -6575,7 +6575,7 @@
6575
  "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
6576
  "status": "pending",
6577
  "episode_id": null,
6578
- "run_status": "queued",
6579
  "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
6580
  "planned_protocol": {
6581
  "episodes": 1,
 
6
  "benchmark_complete": false,
7
  "edition": "codex-simple-astra-high-seed0",
8
  "created_at": "2026-10-09T00:09:42.989838+00:00",
9
+ "updated_at": "2026-10-10T01:18:00.915385+00:00",
10
  "model": "gpt-6-astra",
11
  "effort": "high",
12
  "seed": 0,
 
129
  "new_evaluations": 7,
130
  "progress": {
131
  "finished": 79,
132
+ "running": 3,
133
+ "queued": 2,
134
  "needs_review": 0,
135
  "interrupted": 0,
136
  "native_successes": 51,
 
6575
  "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
6576
  "status": "pending",
6577
  "episode_id": null,
6578
+ "run_status": "running",
6579
  "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
6580
  "planned_protocol": {
6581
  "episodes": 1,
manifest.json CHANGED
@@ -19,7 +19,7 @@
19
  "catalog/task06/11-push-office-chair/task.yaml": "ab19bf9b7cec8992e2dcc1fb30ad9f6ce0f8343063b44777b2b68afc39d7f426",
20
  "catalog/task06/12-open-trash-can/task.yaml": "8d8b4b0ec848f91283e73416d257f5b0f816ac4b872fccd10b213e74d953085c",
21
  "comparison.json": "487d479f3d03e72efaf3c19c1e63f5894bcfea2954cb1cc46327c379b5315ad3",
22
- "data.json": "68723065582e3410bbe58c10ec0d741db514e3906b2954e5bdfe89e908897bd3",
23
  "episodes.csv": "3d88b62d09ca6f64a6932942d21bbd46142f44c5403ab465abcbaf70227c3cd5",
24
  "episodes.json": "66b5a163d5b639b1d3bd2e4232083e030d5b6e5e41caccf560a8617e973de2ee",
25
  "failure-reviews.json": "c66a997c9ecd6f7f43f130a8a33cd64c7a5b2049033e9ccde653ee30e4796f23",
@@ -32,6 +32,6 @@
32
  "licenses/robosuite-LICENSE.txt": "177978cbece0a4c454c2aaec5b3f145b39270814874c43109da9e829c39d9cba",
33
  "protocol.json": "a3288345609e793384a1cf99eea6b07a451a302282082dc4c1e0714ea0b35859",
34
  "style.css": "dd31b30951c220ebb82bc96224b5e640913945679e42b2e0a42e2c373a329e6c",
35
- "summary.json": "ad2e7abe9bb7b64b5595d475387e09d8cf0594c4649de3a40c5b44a9ead0320e",
36
- "task-index.json": "3204f3f6a40374ab9781611f94cd8177f8af7295a1b96bfb2547d76aba56d334"
37
  }
 
19
  "catalog/task06/11-push-office-chair/task.yaml": "ab19bf9b7cec8992e2dcc1fb30ad9f6ce0f8343063b44777b2b68afc39d7f426",
20
  "catalog/task06/12-open-trash-can/task.yaml": "8d8b4b0ec848f91283e73416d257f5b0f816ac4b872fccd10b213e74d953085c",
21
  "comparison.json": "487d479f3d03e72efaf3c19c1e63f5894bcfea2954cb1cc46327c379b5315ad3",
22
+ "data.json": "778e49376f6133719890725e55fa81fde807327874d39f9d7741dad7a5808d8f",
23
  "episodes.csv": "3d88b62d09ca6f64a6932942d21bbd46142f44c5403ab465abcbaf70227c3cd5",
24
  "episodes.json": "66b5a163d5b639b1d3bd2e4232083e030d5b6e5e41caccf560a8617e973de2ee",
25
  "failure-reviews.json": "c66a997c9ecd6f7f43f130a8a33cd64c7a5b2049033e9ccde653ee30e4796f23",
 
32
  "licenses/robosuite-LICENSE.txt": "177978cbece0a4c454c2aaec5b3f145b39270814874c43109da9e829c39d9cba",
33
  "protocol.json": "a3288345609e793384a1cf99eea6b07a451a302282082dc4c1e0714ea0b35859",
34
  "style.css": "dd31b30951c220ebb82bc96224b5e640913945679e42b2e0a42e2c373a329e6c",
35
+ "summary.json": "71ec7e4438a0333ea048aad0d3bc8c4e5f558b03a885afdda327d7a74ce7b5c3",
36
+ "task-index.json": "26fea0071532a894ffee5fe88af6a7e80a8320bd0b1c6026c742ef5947a04f72"
37
  }
publication-manifest.json CHANGED
@@ -82,8 +82,8 @@
82
  "bytes": 134701
83
  },
84
  "data.json": {
85
- "sha256": "68723065582e3410bbe58c10ec0d741db514e3906b2954e5bdfe89e908897bd3",
86
- "bytes": 1154072
87
  },
88
  "episodes.csv": {
89
  "sha256": "3d88b62d09ca6f64a6932942d21bbd46142f44c5403ab465abcbaf70227c3cd5",
@@ -134,15 +134,15 @@
134
  "bytes": 16560
135
  },
136
  "summary.json": {
137
- "sha256": "ad2e7abe9bb7b64b5595d475387e09d8cf0594c4649de3a40c5b44a9ead0320e",
138
  "bytes": 3221
139
  },
140
  "task-index.json": {
141
- "sha256": "3204f3f6a40374ab9781611f94cd8177f8af7295a1b96bfb2547d76aba56d334",
142
- "bytes": 229778
143
  },
144
  "manifest.json": {
145
- "sha256": "f823b7b320bf37ec64e46d869eb8352532532ca1773cae84c3fec614b1047a26",
146
  "bytes": 3481
147
  }
148
  }
 
82
  "bytes": 134701
83
  },
84
  "data.json": {
85
+ "sha256": "778e49376f6133719890725e55fa81fde807327874d39f9d7741dad7a5808d8f",
86
+ "bytes": 1154073
87
  },
88
  "episodes.csv": {
89
  "sha256": "3d88b62d09ca6f64a6932942d21bbd46142f44c5403ab465abcbaf70227c3cd5",
 
134
  "bytes": 16560
135
  },
136
  "summary.json": {
137
+ "sha256": "71ec7e4438a0333ea048aad0d3bc8c4e5f558b03a885afdda327d7a74ce7b5c3",
138
  "bytes": 3221
139
  },
140
  "task-index.json": {
141
+ "sha256": "26fea0071532a894ffee5fe88af6a7e80a8320bd0b1c6026c742ef5947a04f72",
142
+ "bytes": 229779
143
  },
144
  "manifest.json": {
145
+ "sha256": "887c8f7adde67c1b8241fc55b1a7989ec471bc81b41f3318d98864172bf09f9f",
146
  "bytes": 3481
147
  }
148
  }
summary.json CHANGED
@@ -112,8 +112,8 @@
112
  "new_evaluations": 7,
113
  "progress": {
114
  "finished": 79,
115
- "running": 2,
116
- "queued": 3,
117
  "needs_review": 0,
118
  "interrupted": 0,
119
  "native_successes": 51,
 
112
  "new_evaluations": 7,
113
  "progress": {
114
  "finished": 79,
115
+ "running": 3,
116
+ "queued": 2,
117
  "needs_review": 0,
118
  "interrupted": 0,
119
  "native_successes": 51,
task-index.json CHANGED
@@ -6324,7 +6324,7 @@
6324
  "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
6325
  "status": "pending",
6326
  "episode_id": null,
6327
- "run_status": "queued",
6328
  "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
6329
  "planned_protocol": {
6330
  "episodes": 1,
 
6324
  "instruction_source": "Unchanged native SIMPLE instruction for the effective default task configuration.",
6325
  "status": "pending",
6326
  "episode_id": null,
6327
+ "run_status": "running",
6328
  "status_note": "Authorized episode is queued, running, or awaiting evidence review.",
6329
  "planned_protocol": {
6330
  "episodes": 1,