cy0307 commited on
Commit
b9dbf0b
·
verified ·
1 Parent(s): c49778a

Add files using upload-large-folder tool

Browse files
Files changed (27) hide show
  1. docs/data/artifact_index.json +21 -21
  2. docs/data/episode128_task_model_radar.json +26 -26
  3. docs/data/mirror_parity.json +208 -183
  4. docs/data/publication_audit.json +4 -3
  5. docs/data/quality_gates.json +1 -1
  6. docs/data/scope_claims_audit.json +1 -1
  7. docs/data/single_episode_task_model_radar.json +1 -1
  8. docs/data/source_alignment_audit.json +1 -1
  9. docs/data/task_method_20_gap_audit.json +11 -25
  10. docs/data/task_method_20_result_matrix.json +18 -18
  11. docs/data/unified_task_model_radar.json +30 -30
  12. results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/RUN_REPORT.md +8 -0
  13. results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/collection_validation.json +16 -0
  14. results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json +25 -0
  15. results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/launch_env.txt +11 -0
  16. results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/summary.json +19 -0
  17. results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z_shard0.progress.jsonl +0 -0
  18. results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z_shard1.progress.jsonl +0 -0
  19. results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/RUN_REPORT.md +8 -0
  20. results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/caption_grounding/metrics.json +24 -0
  21. results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/caption_grounding/predictions.csv +0 -0
  22. results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/collection_validation.json +16 -0
  23. results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/launch_env.txt +11 -0
  24. results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/summary.json +19 -0
  25. results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z_shard0.progress.jsonl +0 -0
  26. results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z_shard1.progress.jsonl +0 -0
  27. scripts/omni/collect_qwen3_retrieval_task_probe_results.sh +89 -0
docs/data/artifact_index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "title": "Ropedia Xperience-10M Task Suite Artifact Index",
3
- "generated_at_utc": "2026-06-18T09:28:32+00:00",
4
  "status": "pass",
5
  "artifact_count": 213,
6
  "missing": [],
@@ -599,7 +599,7 @@
599
  "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
600
  "exists": true,
601
  "bytes": 4432,
602
- "sha256": "499e62359f6db0afa32c1160a2c4ca90da511c1035efaac4e77943c4905751a7"
603
  },
604
  {
605
  "id": "source_alignment_validator",
@@ -719,8 +719,8 @@
719
  "surface": "website_hf",
720
  "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3/Cosmos overlay mappings, branch-card caveats, and explicit scoreless status records.",
721
  "exists": true,
722
- "bytes": 231127,
723
- "sha256": "3bcabe4b7182b66292c012f26401d753f581d9feb3d0adb312a5115933f34767"
724
  },
725
  {
726
  "id": "single_episode_task_model_radar_json",
@@ -731,7 +731,7 @@
731
  "shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
732
  "exists": true,
733
  "bytes": 50973,
734
- "sha256": "01d524bca7b7a827134ac00af76659745f6c2127096064078f99c3db151cc7e0"
735
  },
736
  {
737
  "id": "episode128_task_model_radar_json",
@@ -741,8 +741,8 @@
741
  "surface": "website_hf",
742
  "shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines and verified Qwen3/Cosmos branches, preserving explicit scoreless cells.",
743
  "exists": true,
744
- "bytes": 187275,
745
- "sha256": "e006cb7f6c0c8bf7258a42206ec095b4ad2622c4bd7b9f67275d8a9cae2105a5"
746
  },
747
  {
748
  "id": "task_method_20_result_matrix_json",
@@ -752,8 +752,8 @@
752
  "surface": "website_hf",
753
  "shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and scoreless cells carry unsupported/not-evaluated reasons.",
754
  "exists": true,
755
- "bytes": 129689,
756
- "sha256": "d633cbc900b04df4afef67a75a9d17d79c9da2942a43ab0d5d31dcf270af2c94"
757
  },
758
  {
759
  "id": "task_method_20_result_matrix",
@@ -763,8 +763,8 @@
763
  "surface": "repo_hf",
764
  "shows": "Reader-facing table that separates 20 records per method from numeric scored axes, documented raw128 proxy scores, unsupported metadata targets, and model targets not evaluated in verified packages.",
765
  "exists": true,
766
- "bytes": 4152,
767
- "sha256": "c5ce3d4dc21751dc0b7e371ac0d92790190e306f48b0147d99952646ae2dedb1"
768
  },
769
  {
770
  "id": "task_method_20_gap_audit_json",
@@ -774,8 +774,8 @@
774
  "surface": "website_hf",
775
  "shows": "Machine-readable 180-record gap ledger with numeric scores, scoreless cells, explicit status reasons, and next evidence needed before new scores can be published.",
776
  "exists": true,
777
- "bytes": 52867,
778
- "sha256": "255ba3324994ee1848a99f6bc08b74b447a63a18638d43b93017dbb591b19c6d"
779
  },
780
  {
781
  "id": "task_method_20_gap_audit",
@@ -785,8 +785,8 @@
785
  "surface": "repo_hf",
786
  "shows": "Reader-facing ledger that lists every scoreless method-task cell and the concrete target or model-output evidence required before it can become numeric.",
787
  "exists": true,
788
- "bytes": 14981,
789
- "sha256": "90f9885e601b2f19af863650fae7821092147ada1d86bb945b08c3cd603197ac"
790
  },
791
  {
792
  "id": "unified_task_model_radar_chart",
@@ -796,8 +796,8 @@
796
  "surface": "website_hf",
797
  "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3/Cosmos task-aligned model overlays.",
798
  "exists": true,
799
- "bytes": 50506,
800
- "sha256": "890cbddb57e241e4360c96c18a013c98ed56d26711f136babac6e3313751bbfb"
801
  },
802
  {
803
  "id": "single_episode_task_model_radar_chart",
@@ -818,8 +818,8 @@
818
  "surface": "website_hf",
819
  "shows": "Separates the selected 128-episode methods: raw-feature simple/NN as complete 20/20 scored polygons and metadata/Qwen/Cosmos as task-aligned overlays.",
820
  "exists": true,
821
- "bytes": 44490,
822
- "sha256": "537c0dc2f1173bc40aaa216cbf760aeea30c9325ddd5c08e1f16e476d4c01bdd"
823
  },
824
  {
825
  "id": "unified_task_model_radar_builder",
@@ -1105,7 +1105,7 @@
1105
  "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
1106
  "exists": true,
1107
  "bytes": 8100,
1108
- "sha256": "42938d8fe2b86f4f74f27138c8099cc65bb37c092100544cda0913bf29144e09"
1109
  },
1110
  {
1111
  "id": "public_surface_qa",
@@ -1286,7 +1286,7 @@
1286
  "volatile": true,
1287
  "shows": "Confirms public bundles exclude raw data, caches, heavy archives, and credential text.",
1288
  "exists": true,
1289
- "bytes": 9341,
1290
  "hash_policy": "existence_and_size_only"
1291
  },
1292
  {
 
1
  {
2
  "title": "Ropedia Xperience-10M Task Suite Artifact Index",
3
+ "generated_at_utc": "2026-06-18T10:04:51+00:00",
4
  "status": "pass",
5
  "artifact_count": 213,
6
  "missing": [],
 
599
  "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
600
  "exists": true,
601
  "bytes": 4432,
602
+ "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
603
  },
604
  {
605
  "id": "source_alignment_validator",
 
719
  "surface": "website_hf",
720
  "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3/Cosmos overlay mappings, branch-card caveats, and explicit scoreless status records.",
721
  "exists": true,
722
+ "bytes": 231123,
723
+ "sha256": "c004d35f0a3e0073c4116dd79a2bcdaac872605d715a7eccdaa15787df800f07"
724
  },
725
  {
726
  "id": "single_episode_task_model_radar_json",
 
731
  "shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
732
  "exists": true,
733
  "bytes": 50973,
734
+ "sha256": "6db28943d1206aef75fbce8ea87ea52a35c0144c6186214f37da9311ca8c9a0c"
735
  },
736
  {
737
  "id": "episode128_task_model_radar_json",
 
741
  "surface": "website_hf",
742
  "shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines and verified Qwen3/Cosmos branches, preserving explicit scoreless cells.",
743
  "exists": true,
744
+ "bytes": 187271,
745
+ "sha256": "acd8623ad19bf0d0ee1ffb434ecefa087339b59e97d30809eca9b739f83f1a89"
746
  },
747
  {
748
  "id": "task_method_20_result_matrix_json",
 
752
  "surface": "website_hf",
753
  "shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and scoreless cells carry unsupported/not-evaluated reasons.",
754
  "exists": true,
755
+ "bytes": 129687,
756
+ "sha256": "e5d3fa22013fedf350907746f775cc4a1ca3bb3f816b40ca9467d51cf16925f8"
757
  },
758
  {
759
  "id": "task_method_20_result_matrix",
 
763
  "surface": "repo_hf",
764
  "shows": "Reader-facing table that separates 20 records per method from numeric scored axes, documented raw128 proxy scores, unsupported metadata targets, and model targets not evaluated in verified packages.",
765
  "exists": true,
766
+ "bytes": 4144,
767
+ "sha256": "dac2828ba0286bc35290a61b6d02dbd75f0b3acb8d47a73cfa7f072d7fa209c1"
768
  },
769
  {
770
  "id": "task_method_20_gap_audit_json",
 
774
  "surface": "website_hf",
775
  "shows": "Machine-readable 180-record gap ledger with numeric scores, scoreless cells, explicit status reasons, and next evidence needed before new scores can be published.",
776
  "exists": true,
777
+ "bytes": 52153,
778
+ "sha256": "e47ac5d2ac8216f2b46b5fb868275c779226dce8089a8c025dd26571cb5758d3"
779
  },
780
  {
781
  "id": "task_method_20_gap_audit",
 
785
  "surface": "repo_hf",
786
  "shows": "Reader-facing ledger that lists every scoreless method-task cell and the concrete target or model-output evidence required before it can become numeric.",
787
  "exists": true,
788
+ "bytes": 14812,
789
+ "sha256": "d2f0228497fa834c7f097e1fe74e2210b85d0a01f7841356e67dc79929a74413"
790
  },
791
  {
792
  "id": "unified_task_model_radar_chart",
 
796
  "surface": "website_hf",
797
  "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3/Cosmos task-aligned model overlays.",
798
  "exists": true,
799
+ "bytes": 50618,
800
+ "sha256": "29ede875ef96c76a8aa7ec6e9883457be611fac8ef967b825041b33fe1d86863"
801
  },
802
  {
803
  "id": "single_episode_task_model_radar_chart",
 
818
  "surface": "website_hf",
819
  "shows": "Separates the selected 128-episode methods: raw-feature simple/NN as complete 20/20 scored polygons and metadata/Qwen/Cosmos as task-aligned overlays.",
820
  "exists": true,
821
+ "bytes": 44602,
822
+ "sha256": "9a2fd542502cb26f093097d9ace238f8cf3b619e0abdec5bf2870c5271fb9ed5"
823
  },
824
  {
825
  "id": "unified_task_model_radar_builder",
 
1105
  "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
1106
  "exists": true,
1107
  "bytes": 8100,
1108
+ "sha256": "0ccb122c1425ef617e7a175ff38cdda9977e737879e609f77fcec2684f4057d4"
1109
  },
1110
  {
1111
  "id": "public_surface_qa",
 
1286
  "volatile": true,
1287
  "shows": "Confirms public bundles exclude raw data, caches, heavy archives, and credential text.",
1288
  "exists": true,
1289
+ "bytes": 9526,
1290
  "hash_policy": "existence_and_size_only"
1291
  },
1292
  {
docs/data/episode128_task_model_radar.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "title": "128-Episode 20-Task Radar",
3
  "status": "pass",
4
- "generated_at_utc": "2026-06-18T09:06:25+00:00",
5
  "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3/Cosmos branches. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.",
6
  "task_count": 20,
7
  "method_count": 7,
8
  "method_task_record_count": 140,
9
- "scored_method_task_count": 80,
10
  "normalization_policy": {
11
  "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
12
  "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -127,17 +127,17 @@
127
  "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future-task probes scored from task-specific JSON.",
128
  "plotted_as": "colored point overlay",
129
  "result_record_count": 20,
130
- "scored_task_count": 14,
131
- "covered_task_count": 14,
132
  "proxy_scored_task_count": 0,
133
- "scoreless_task_count": 6,
134
  "unsupported_task_count": 0,
135
- "not_evaluated_task_count": 6,
136
  "status_counts": {
137
- "not_evaluated_in_verified_package": 6,
138
- "scored": 14
139
  },
140
- "coverage_fraction": 0.7,
141
  "result_record_fraction": 1.0
142
  },
143
  {
@@ -975,15 +975,15 @@
975
  "status_label": "scored"
976
  },
977
  "qwen3_omni_v6_lora": {
978
- "raw": null,
979
- "metric_key": "mrr",
980
- "source": null,
981
  "scope": "multi_episode_128_partial_model_overlay",
982
- "status": "not_evaluated_in_verified_package",
983
- "reason": "the verified public model package did not ask this branch to emit that task target; a new task-specific evaluation package is required for a numeric score",
984
- "normalized_score": null,
985
- "raw_text": "n/a",
986
- "status_label": "not evaluated"
987
  },
988
  "cosmos3_super_reasoner": {
989
  "raw": null,
@@ -3098,17 +3098,17 @@
3098
  "task_label": "Cross-Modal Retrieval",
3099
  "series_id": "qwen3_omni_v6_lora",
3100
  "method": "Qwen3-Omni v6 LoRA",
3101
- "status": "not_evaluated_in_verified_package",
3102
- "status_label": "not evaluated",
3103
- "scored": false,
3104
  "proxy_scored": false,
3105
- "raw": null,
3106
- "raw_text": "n/a",
3107
- "normalized_score": null,
3108
- "metric_key": "mrr",
3109
- "source": null,
3110
  "scope": "multi_episode_128_partial_model_overlay",
3111
- "reason": "the verified public model package did not ask this branch to emit that task target; a new task-specific evaluation package is required for a numeric score"
3112
  },
3113
  {
3114
  "task_number": 9,
 
1
  {
2
  "title": "128-Episode 20-Task Radar",
3
  "status": "pass",
4
+ "generated_at_utc": "2026-06-18T10:04:17+00:00",
5
  "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3/Cosmos branches. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.",
6
  "task_count": 20,
7
  "method_count": 7,
8
  "method_task_record_count": 140,
9
+ "scored_method_task_count": 81,
10
  "normalization_policy": {
11
  "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
12
  "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
 
127
  "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future-task probes scored from task-specific JSON.",
128
  "plotted_as": "colored point overlay",
129
  "result_record_count": 20,
130
+ "scored_task_count": 15,
131
+ "covered_task_count": 15,
132
  "proxy_scored_task_count": 0,
133
+ "scoreless_task_count": 5,
134
  "unsupported_task_count": 0,
135
+ "not_evaluated_task_count": 5,
136
  "status_counts": {
137
+ "not_evaluated_in_verified_package": 5,
138
+ "scored": 15
139
  },
140
+ "coverage_fraction": 0.75,
141
  "result_record_fraction": 1.0
142
  },
143
  {
 
975
  "status_label": "scored"
976
  },
977
  "qwen3_omni_v6_lora": {
978
+ "raw": 0.5080191798941732,
979
+ "metric_key": "cross_modal_retrieval_mrr",
980
+ "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json",
981
  "scope": "multi_episode_128_partial_model_overlay",
982
+ "status": "scored",
983
+ "reason": null,
984
+ "normalized_score": 0.5080191798941732,
985
+ "raw_text": "0.5080",
986
+ "status_label": "scored"
987
  },
988
  "cosmos3_super_reasoner": {
989
  "raw": null,
 
3098
  "task_label": "Cross-Modal Retrieval",
3099
  "series_id": "qwen3_omni_v6_lora",
3100
  "method": "Qwen3-Omni v6 LoRA",
3101
+ "status": "scored",
3102
+ "status_label": "scored",
3103
+ "scored": true,
3104
  "proxy_scored": false,
3105
+ "raw": 0.5080191798941732,
3106
+ "raw_text": "0.5080",
3107
+ "normalized_score": 0.5080191798941732,
3108
+ "metric_key": "cross_modal_retrieval_mrr",
3109
+ "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json",
3110
  "scope": "multi_episode_128_partial_model_overlay",
3111
+ "reason": null
3112
  },
3113
  {
3114
  "task_number": 9,
docs/data/mirror_parity.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "status": "pass",
3
- "generated_at_utc": "2026-06-18T09:30:32+00:00",
4
  "hf_root": "hf_publish",
5
  "summary": {
6
- "group_count": 649,
7
  "failure_count": 0,
8
  "failures_by_surface": {}
9
  },
@@ -139,44 +139,44 @@
139
  "path": "repo:docs/data/artifact_index.json",
140
  "exists": true,
141
  "bytes": 116109,
142
- "sha256": "5612f2381bcca2a21d585efa3d98d8017a799c164057cb5c03e8b9ed1080423f"
143
  },
144
  "mirrors": {
145
  "hf_space": {
146
  "path": "hf_space:data/artifact_index.json",
147
  "exists": true,
148
  "bytes": 116109,
149
- "sha256": "5612f2381bcca2a21d585efa3d98d8017a799c164057cb5c03e8b9ed1080423f"
150
  },
151
  "hf_artifacts_data": {
152
  "path": "hf_artifacts:data/artifact_index.json",
153
  "exists": true,
154
  "bytes": 116109,
155
- "sha256": "5612f2381bcca2a21d585efa3d98d8017a799c164057cb5c03e8b9ed1080423f"
156
  },
157
  "hf_artifacts": {
158
  "path": "hf_artifacts:docs/data/artifact_index.json",
159
  "exists": true,
160
  "bytes": 116109,
161
- "sha256": "5612f2381bcca2a21d585efa3d98d8017a799c164057cb5c03e8b9ed1080423f"
162
  },
163
  "hf_model_data": {
164
  "path": "hf_model:data/artifact_index.json",
165
  "exists": true,
166
  "bytes": 116109,
167
- "sha256": "5612f2381bcca2a21d585efa3d98d8017a799c164057cb5c03e8b9ed1080423f"
168
  },
169
  "hf_model_docs_data": {
170
  "path": "hf_model:docs/data/artifact_index.json",
171
  "exists": true,
172
  "bytes": 116109,
173
- "sha256": "5612f2381bcca2a21d585efa3d98d8017a799c164057cb5c03e8b9ed1080423f"
174
  },
175
  "hf_model": {
176
  "path": "hf_model:metrics/artifact_index.json",
177
  "exists": true,
178
  "bytes": 116109,
179
- "sha256": "5612f2381bcca2a21d585efa3d98d8017a799c164057cb5c03e8b9ed1080423f"
180
  }
181
  },
182
  "failures": []
@@ -335,44 +335,44 @@
335
  "path": "repo:docs/data/figure_index.json",
336
  "exists": true,
337
  "bytes": 19441,
338
- "sha256": "7f641c6c5a595de09d291f17e4e2aad06a3cee73b6c64608220bf69996f0e581"
339
  },
340
  "mirrors": {
341
  "hf_space": {
342
  "path": "hf_space:data/figure_index.json",
343
  "exists": true,
344
  "bytes": 19441,
345
- "sha256": "7f641c6c5a595de09d291f17e4e2aad06a3cee73b6c64608220bf69996f0e581"
346
  },
347
  "hf_artifacts_data": {
348
  "path": "hf_artifacts:data/figure_index.json",
349
  "exists": true,
350
  "bytes": 19441,
351
- "sha256": "7f641c6c5a595de09d291f17e4e2aad06a3cee73b6c64608220bf69996f0e581"
352
  },
353
  "hf_artifacts": {
354
  "path": "hf_artifacts:docs/data/figure_index.json",
355
  "exists": true,
356
  "bytes": 19441,
357
- "sha256": "7f641c6c5a595de09d291f17e4e2aad06a3cee73b6c64608220bf69996f0e581"
358
  },
359
  "hf_model_data": {
360
  "path": "hf_model:data/figure_index.json",
361
  "exists": true,
362
  "bytes": 19441,
363
- "sha256": "7f641c6c5a595de09d291f17e4e2aad06a3cee73b6c64608220bf69996f0e581"
364
  },
365
  "hf_model_docs_data": {
366
  "path": "hf_model:docs/data/figure_index.json",
367
  "exists": true,
368
  "bytes": 19441,
369
- "sha256": "7f641c6c5a595de09d291f17e4e2aad06a3cee73b6c64608220bf69996f0e581"
370
  },
371
  "hf_model": {
372
  "path": "hf_model:metrics/figure_index.json",
373
  "exists": true,
374
  "bytes": 19441,
375
- "sha256": "7f641c6c5a595de09d291f17e4e2aad06a3cee73b6c64608220bf69996f0e581"
376
  }
377
  },
378
  "failures": []
@@ -922,45 +922,45 @@
922
  "local": {
923
  "path": "repo:docs/data/publication_audit.json",
924
  "exists": true,
925
- "bytes": 9526,
926
- "sha256": "25759aa29d95fa065a9fe3ec74fb3781e8d5858ac6ca2553c7b2d29c48bbb93d"
927
  },
928
  "mirrors": {
929
  "hf_space": {
930
  "path": "hf_space:data/publication_audit.json",
931
  "exists": true,
932
- "bytes": 9526,
933
- "sha256": "25759aa29d95fa065a9fe3ec74fb3781e8d5858ac6ca2553c7b2d29c48bbb93d"
934
  },
935
  "hf_artifacts_data": {
936
  "path": "hf_artifacts:data/publication_audit.json",
937
  "exists": true,
938
- "bytes": 9526,
939
- "sha256": "25759aa29d95fa065a9fe3ec74fb3781e8d5858ac6ca2553c7b2d29c48bbb93d"
940
  },
941
  "hf_artifacts": {
942
  "path": "hf_artifacts:docs/data/publication_audit.json",
943
  "exists": true,
944
- "bytes": 9526,
945
- "sha256": "25759aa29d95fa065a9fe3ec74fb3781e8d5858ac6ca2553c7b2d29c48bbb93d"
946
  },
947
  "hf_model_data": {
948
  "path": "hf_model:data/publication_audit.json",
949
  "exists": true,
950
- "bytes": 9526,
951
- "sha256": "25759aa29d95fa065a9fe3ec74fb3781e8d5858ac6ca2553c7b2d29c48bbb93d"
952
  },
953
  "hf_model_docs_data": {
954
  "path": "hf_model:docs/data/publication_audit.json",
955
  "exists": true,
956
- "bytes": 9526,
957
- "sha256": "25759aa29d95fa065a9fe3ec74fb3781e8d5858ac6ca2553c7b2d29c48bbb93d"
958
  },
959
  "hf_model": {
960
  "path": "hf_model:metrics/publication_audit.json",
961
  "exists": true,
962
- "bytes": 9526,
963
- "sha256": "25759aa29d95fa065a9fe3ec74fb3781e8d5858ac6ca2553c7b2d29c48bbb93d"
964
  }
965
  },
966
  "failures": []
@@ -972,44 +972,44 @@
972
  "path": "repo:docs/data/public_surface_qa.json",
973
  "exists": true,
974
  "bytes": 7126,
975
- "sha256": "97f7e2df04f2b88ce9f2957037da201619e97220d8a72cee572ab4d1cecedb72"
976
  },
977
  "mirrors": {
978
  "hf_space": {
979
  "path": "hf_space:data/public_surface_qa.json",
980
  "exists": true,
981
  "bytes": 7126,
982
- "sha256": "97f7e2df04f2b88ce9f2957037da201619e97220d8a72cee572ab4d1cecedb72"
983
  },
984
  "hf_artifacts_data": {
985
  "path": "hf_artifacts:data/public_surface_qa.json",
986
  "exists": true,
987
  "bytes": 7126,
988
- "sha256": "97f7e2df04f2b88ce9f2957037da201619e97220d8a72cee572ab4d1cecedb72"
989
  },
990
  "hf_artifacts": {
991
  "path": "hf_artifacts:docs/data/public_surface_qa.json",
992
  "exists": true,
993
  "bytes": 7126,
994
- "sha256": "97f7e2df04f2b88ce9f2957037da201619e97220d8a72cee572ab4d1cecedb72"
995
  },
996
  "hf_model_data": {
997
  "path": "hf_model:data/public_surface_qa.json",
998
  "exists": true,
999
  "bytes": 7126,
1000
- "sha256": "97f7e2df04f2b88ce9f2957037da201619e97220d8a72cee572ab4d1cecedb72"
1001
  },
1002
  "hf_model_docs_data": {
1003
  "path": "hf_model:docs/data/public_surface_qa.json",
1004
  "exists": true,
1005
  "bytes": 7126,
1006
- "sha256": "97f7e2df04f2b88ce9f2957037da201619e97220d8a72cee572ab4d1cecedb72"
1007
  },
1008
  "hf_model": {
1009
  "path": "hf_model:metrics/public_surface_qa.json",
1010
  "exists": true,
1011
  "bytes": 7126,
1012
- "sha256": "97f7e2df04f2b88ce9f2957037da201619e97220d8a72cee572ab4d1cecedb72"
1013
  }
1014
  },
1015
  "failures": []
@@ -1119,44 +1119,44 @@
1119
  "path": "repo:docs/data/quality_gates.json",
1120
  "exists": true,
1121
  "bytes": 8100,
1122
- "sha256": "b5e7b11d54cc3234e57e9272406a0ffca1e5bb4ad42a45b30d9493ed8d82b4bf"
1123
  },
1124
  "mirrors": {
1125
  "hf_space": {
1126
  "path": "hf_space:data/quality_gates.json",
1127
  "exists": true,
1128
  "bytes": 8100,
1129
- "sha256": "b5e7b11d54cc3234e57e9272406a0ffca1e5bb4ad42a45b30d9493ed8d82b4bf"
1130
  },
1131
  "hf_artifacts_data": {
1132
  "path": "hf_artifacts:data/quality_gates.json",
1133
  "exists": true,
1134
  "bytes": 8100,
1135
- "sha256": "b5e7b11d54cc3234e57e9272406a0ffca1e5bb4ad42a45b30d9493ed8d82b4bf"
1136
  },
1137
  "hf_artifacts": {
1138
  "path": "hf_artifacts:docs/data/quality_gates.json",
1139
  "exists": true,
1140
  "bytes": 8100,
1141
- "sha256": "b5e7b11d54cc3234e57e9272406a0ffca1e5bb4ad42a45b30d9493ed8d82b4bf"
1142
  },
1143
  "hf_model_data": {
1144
  "path": "hf_model:data/quality_gates.json",
1145
  "exists": true,
1146
  "bytes": 8100,
1147
- "sha256": "b5e7b11d54cc3234e57e9272406a0ffca1e5bb4ad42a45b30d9493ed8d82b4bf"
1148
  },
1149
  "hf_model_docs_data": {
1150
  "path": "hf_model:docs/data/quality_gates.json",
1151
  "exists": true,
1152
  "bytes": 8100,
1153
- "sha256": "b5e7b11d54cc3234e57e9272406a0ffca1e5bb4ad42a45b30d9493ed8d82b4bf"
1154
  },
1155
  "hf_model": {
1156
  "path": "hf_model:metrics/quality_gates.json",
1157
  "exists": true,
1158
  "bytes": 8100,
1159
- "sha256": "b5e7b11d54cc3234e57e9272406a0ffca1e5bb4ad42a45b30d9493ed8d82b4bf"
1160
  }
1161
  },
1162
  "failures": []
@@ -1560,44 +1560,44 @@
1560
  "path": "repo:docs/data/scope_claims_audit.json",
1561
  "exists": true,
1562
  "bytes": 21630,
1563
- "sha256": "6df6428701f8becd539f3bbdd80caabd69a0c51b29a3a78f08a2cf64523e8593"
1564
  },
1565
  "mirrors": {
1566
  "hf_space": {
1567
  "path": "hf_space:data/scope_claims_audit.json",
1568
  "exists": true,
1569
  "bytes": 21630,
1570
- "sha256": "6df6428701f8becd539f3bbdd80caabd69a0c51b29a3a78f08a2cf64523e8593"
1571
  },
1572
  "hf_artifacts_data": {
1573
  "path": "hf_artifacts:data/scope_claims_audit.json",
1574
  "exists": true,
1575
  "bytes": 21630,
1576
- "sha256": "6df6428701f8becd539f3bbdd80caabd69a0c51b29a3a78f08a2cf64523e8593"
1577
  },
1578
  "hf_artifacts": {
1579
  "path": "hf_artifacts:docs/data/scope_claims_audit.json",
1580
  "exists": true,
1581
  "bytes": 21630,
1582
- "sha256": "6df6428701f8becd539f3bbdd80caabd69a0c51b29a3a78f08a2cf64523e8593"
1583
  },
1584
  "hf_model_data": {
1585
  "path": "hf_model:data/scope_claims_audit.json",
1586
  "exists": true,
1587
  "bytes": 21630,
1588
- "sha256": "6df6428701f8becd539f3bbdd80caabd69a0c51b29a3a78f08a2cf64523e8593"
1589
  },
1590
  "hf_model_docs_data": {
1591
  "path": "hf_model:docs/data/scope_claims_audit.json",
1592
  "exists": true,
1593
  "bytes": 21630,
1594
- "sha256": "6df6428701f8becd539f3bbdd80caabd69a0c51b29a3a78f08a2cf64523e8593"
1595
  },
1596
  "hf_model": {
1597
  "path": "hf_model:metrics/scope_claims_audit.json",
1598
  "exists": true,
1599
  "bytes": 21630,
1600
- "sha256": "6df6428701f8becd539f3bbdd80caabd69a0c51b29a3a78f08a2cf64523e8593"
1601
  }
1602
  },
1603
  "failures": []
@@ -1658,44 +1658,44 @@
1658
  "path": "repo:docs/data/source_alignment_audit.json",
1659
  "exists": true,
1660
  "bytes": 4432,
1661
- "sha256": "499e62359f6db0afa32c1160a2c4ca90da511c1035efaac4e77943c4905751a7"
1662
  },
1663
  "mirrors": {
1664
  "hf_space": {
1665
  "path": "hf_space:data/source_alignment_audit.json",
1666
  "exists": true,
1667
  "bytes": 4432,
1668
- "sha256": "499e62359f6db0afa32c1160a2c4ca90da511c1035efaac4e77943c4905751a7"
1669
  },
1670
  "hf_artifacts_data": {
1671
  "path": "hf_artifacts:data/source_alignment_audit.json",
1672
  "exists": true,
1673
  "bytes": 4432,
1674
- "sha256": "499e62359f6db0afa32c1160a2c4ca90da511c1035efaac4e77943c4905751a7"
1675
  },
1676
  "hf_artifacts": {
1677
  "path": "hf_artifacts:docs/data/source_alignment_audit.json",
1678
  "exists": true,
1679
  "bytes": 4432,
1680
- "sha256": "499e62359f6db0afa32c1160a2c4ca90da511c1035efaac4e77943c4905751a7"
1681
  },
1682
  "hf_model_data": {
1683
  "path": "hf_model:data/source_alignment_audit.json",
1684
  "exists": true,
1685
  "bytes": 4432,
1686
- "sha256": "499e62359f6db0afa32c1160a2c4ca90da511c1035efaac4e77943c4905751a7"
1687
  },
1688
  "hf_model_docs_data": {
1689
  "path": "hf_model:docs/data/source_alignment_audit.json",
1690
  "exists": true,
1691
  "bytes": 4432,
1692
- "sha256": "499e62359f6db0afa32c1160a2c4ca90da511c1035efaac4e77943c4905751a7"
1693
  },
1694
  "hf_model": {
1695
  "path": "hf_model:metrics/source_alignment_audit.json",
1696
  "exists": true,
1697
  "bytes": 4432,
1698
- "sha256": "499e62359f6db0afa32c1160a2c4ca90da511c1035efaac4e77943c4905751a7"
1699
  }
1700
  },
1701
  "failures": []
@@ -1756,44 +1756,44 @@
1756
  "path": "repo:docs/data/single_episode_task_model_radar.json",
1757
  "exists": true,
1758
  "bytes": 50973,
1759
- "sha256": "01d524bca7b7a827134ac00af76659745f6c2127096064078f99c3db151cc7e0"
1760
  },
1761
  "mirrors": {
1762
  "hf_space": {
1763
  "path": "hf_space:data/single_episode_task_model_radar.json",
1764
  "exists": true,
1765
  "bytes": 50973,
1766
- "sha256": "01d524bca7b7a827134ac00af76659745f6c2127096064078f99c3db151cc7e0"
1767
  },
1768
  "hf_artifacts_data": {
1769
  "path": "hf_artifacts:data/single_episode_task_model_radar.json",
1770
  "exists": true,
1771
  "bytes": 50973,
1772
- "sha256": "01d524bca7b7a827134ac00af76659745f6c2127096064078f99c3db151cc7e0"
1773
  },
1774
  "hf_artifacts": {
1775
  "path": "hf_artifacts:docs/data/single_episode_task_model_radar.json",
1776
  "exists": true,
1777
  "bytes": 50973,
1778
- "sha256": "01d524bca7b7a827134ac00af76659745f6c2127096064078f99c3db151cc7e0"
1779
  },
1780
  "hf_model_data": {
1781
  "path": "hf_model:data/single_episode_task_model_radar.json",
1782
  "exists": true,
1783
  "bytes": 50973,
1784
- "sha256": "01d524bca7b7a827134ac00af76659745f6c2127096064078f99c3db151cc7e0"
1785
  },
1786
  "hf_model_docs_data": {
1787
  "path": "hf_model:docs/data/single_episode_task_model_radar.json",
1788
  "exists": true,
1789
  "bytes": 50973,
1790
- "sha256": "01d524bca7b7a827134ac00af76659745f6c2127096064078f99c3db151cc7e0"
1791
  },
1792
  "hf_model": {
1793
  "path": "hf_model:metrics/single_episode_task_model_radar.json",
1794
  "exists": true,
1795
  "bytes": 50973,
1796
- "sha256": "01d524bca7b7a827134ac00af76659745f6c2127096064078f99c3db151cc7e0"
1797
  }
1798
  },
1799
  "failures": []
@@ -1804,45 +1804,45 @@
1804
  "local": {
1805
  "path": "repo:docs/data/episode128_task_model_radar.json",
1806
  "exists": true,
1807
- "bytes": 187275,
1808
- "sha256": "e006cb7f6c0c8bf7258a42206ec095b4ad2622c4bd7b9f67275d8a9cae2105a5"
1809
  },
1810
  "mirrors": {
1811
  "hf_space": {
1812
  "path": "hf_space:data/episode128_task_model_radar.json",
1813
  "exists": true,
1814
- "bytes": 187275,
1815
- "sha256": "e006cb7f6c0c8bf7258a42206ec095b4ad2622c4bd7b9f67275d8a9cae2105a5"
1816
  },
1817
  "hf_artifacts_data": {
1818
  "path": "hf_artifacts:data/episode128_task_model_radar.json",
1819
  "exists": true,
1820
- "bytes": 187275,
1821
- "sha256": "e006cb7f6c0c8bf7258a42206ec095b4ad2622c4bd7b9f67275d8a9cae2105a5"
1822
  },
1823
  "hf_artifacts": {
1824
  "path": "hf_artifacts:docs/data/episode128_task_model_radar.json",
1825
  "exists": true,
1826
- "bytes": 187275,
1827
- "sha256": "e006cb7f6c0c8bf7258a42206ec095b4ad2622c4bd7b9f67275d8a9cae2105a5"
1828
  },
1829
  "hf_model_data": {
1830
  "path": "hf_model:data/episode128_task_model_radar.json",
1831
  "exists": true,
1832
- "bytes": 187275,
1833
- "sha256": "e006cb7f6c0c8bf7258a42206ec095b4ad2622c4bd7b9f67275d8a9cae2105a5"
1834
  },
1835
  "hf_model_docs_data": {
1836
  "path": "hf_model:docs/data/episode128_task_model_radar.json",
1837
  "exists": true,
1838
- "bytes": 187275,
1839
- "sha256": "e006cb7f6c0c8bf7258a42206ec095b4ad2622c4bd7b9f67275d8a9cae2105a5"
1840
  },
1841
  "hf_model": {
1842
  "path": "hf_model:metrics/episode128_task_model_radar.json",
1843
  "exists": true,
1844
- "bytes": 187275,
1845
- "sha256": "e006cb7f6c0c8bf7258a42206ec095b4ad2622c4bd7b9f67275d8a9cae2105a5"
1846
  }
1847
  },
1848
  "failures": []
@@ -2001,44 +2001,44 @@
2001
  "path": "repo:docs/data/task_surface_integrity.json",
2002
  "exists": true,
2003
  "bytes": 45779,
2004
- "sha256": "ab9f1f8b5eb785d72a3e554c041d802cc551787a710af417d1cc04f60c42c6c2"
2005
  },
2006
  "mirrors": {
2007
  "hf_space": {
2008
  "path": "hf_space:data/task_surface_integrity.json",
2009
  "exists": true,
2010
  "bytes": 45779,
2011
- "sha256": "ab9f1f8b5eb785d72a3e554c041d802cc551787a710af417d1cc04f60c42c6c2"
2012
  },
2013
  "hf_artifacts_data": {
2014
  "path": "hf_artifacts:data/task_surface_integrity.json",
2015
  "exists": true,
2016
  "bytes": 45779,
2017
- "sha256": "ab9f1f8b5eb785d72a3e554c041d802cc551787a710af417d1cc04f60c42c6c2"
2018
  },
2019
  "hf_artifacts": {
2020
  "path": "hf_artifacts:docs/data/task_surface_integrity.json",
2021
  "exists": true,
2022
  "bytes": 45779,
2023
- "sha256": "ab9f1f8b5eb785d72a3e554c041d802cc551787a710af417d1cc04f60c42c6c2"
2024
  },
2025
  "hf_model_data": {
2026
  "path": "hf_model:data/task_surface_integrity.json",
2027
  "exists": true,
2028
  "bytes": 45779,
2029
- "sha256": "ab9f1f8b5eb785d72a3e554c041d802cc551787a710af417d1cc04f60c42c6c2"
2030
  },
2031
  "hf_model_docs_data": {
2032
  "path": "hf_model:docs/data/task_surface_integrity.json",
2033
  "exists": true,
2034
  "bytes": 45779,
2035
- "sha256": "ab9f1f8b5eb785d72a3e554c041d802cc551787a710af417d1cc04f60c42c6c2"
2036
  },
2037
  "hf_model": {
2038
  "path": "hf_model:metrics/task_surface_integrity.json",
2039
  "exists": true,
2040
  "bytes": 45779,
2041
- "sha256": "ab9f1f8b5eb785d72a3e554c041d802cc551787a710af417d1cc04f60c42c6c2"
2042
  }
2043
  },
2044
  "failures": []
@@ -2098,45 +2098,45 @@
2098
  "local": {
2099
  "path": "repo:docs/data/task_method_20_result_matrix.json",
2100
  "exists": true,
2101
- "bytes": 129689,
2102
- "sha256": "d633cbc900b04df4afef67a75a9d17d79c9da2942a43ab0d5d31dcf270af2c94"
2103
  },
2104
  "mirrors": {
2105
  "hf_space": {
2106
  "path": "hf_space:data/task_method_20_result_matrix.json",
2107
  "exists": true,
2108
- "bytes": 129689,
2109
- "sha256": "d633cbc900b04df4afef67a75a9d17d79c9da2942a43ab0d5d31dcf270af2c94"
2110
  },
2111
  "hf_artifacts_data": {
2112
  "path": "hf_artifacts:data/task_method_20_result_matrix.json",
2113
  "exists": true,
2114
- "bytes": 129689,
2115
- "sha256": "d633cbc900b04df4afef67a75a9d17d79c9da2942a43ab0d5d31dcf270af2c94"
2116
  },
2117
  "hf_artifacts": {
2118
  "path": "hf_artifacts:docs/data/task_method_20_result_matrix.json",
2119
  "exists": true,
2120
- "bytes": 129689,
2121
- "sha256": "d633cbc900b04df4afef67a75a9d17d79c9da2942a43ab0d5d31dcf270af2c94"
2122
  },
2123
  "hf_model_data": {
2124
  "path": "hf_model:data/task_method_20_result_matrix.json",
2125
  "exists": true,
2126
- "bytes": 129689,
2127
- "sha256": "d633cbc900b04df4afef67a75a9d17d79c9da2942a43ab0d5d31dcf270af2c94"
2128
  },
2129
  "hf_model_docs_data": {
2130
  "path": "hf_model:docs/data/task_method_20_result_matrix.json",
2131
  "exists": true,
2132
- "bytes": 129689,
2133
- "sha256": "d633cbc900b04df4afef67a75a9d17d79c9da2942a43ab0d5d31dcf270af2c94"
2134
  },
2135
  "hf_model": {
2136
  "path": "hf_model:metrics/task_method_20_result_matrix.json",
2137
  "exists": true,
2138
- "bytes": 129689,
2139
- "sha256": "d633cbc900b04df4afef67a75a9d17d79c9da2942a43ab0d5d31dcf270af2c94"
2140
  }
2141
  },
2142
  "failures": []
@@ -2147,45 +2147,45 @@
2147
  "local": {
2148
  "path": "repo:docs/data/task_method_20_gap_audit.json",
2149
  "exists": true,
2150
- "bytes": 52867,
2151
- "sha256": "255ba3324994ee1848a99f6bc08b74b447a63a18638d43b93017dbb591b19c6d"
2152
  },
2153
  "mirrors": {
2154
  "hf_space": {
2155
  "path": "hf_space:data/task_method_20_gap_audit.json",
2156
  "exists": true,
2157
- "bytes": 52867,
2158
- "sha256": "255ba3324994ee1848a99f6bc08b74b447a63a18638d43b93017dbb591b19c6d"
2159
  },
2160
  "hf_artifacts_data": {
2161
  "path": "hf_artifacts:data/task_method_20_gap_audit.json",
2162
  "exists": true,
2163
- "bytes": 52867,
2164
- "sha256": "255ba3324994ee1848a99f6bc08b74b447a63a18638d43b93017dbb591b19c6d"
2165
  },
2166
  "hf_artifacts": {
2167
  "path": "hf_artifacts:docs/data/task_method_20_gap_audit.json",
2168
  "exists": true,
2169
- "bytes": 52867,
2170
- "sha256": "255ba3324994ee1848a99f6bc08b74b447a63a18638d43b93017dbb591b19c6d"
2171
  },
2172
  "hf_model_data": {
2173
  "path": "hf_model:data/task_method_20_gap_audit.json",
2174
  "exists": true,
2175
- "bytes": 52867,
2176
- "sha256": "255ba3324994ee1848a99f6bc08b74b447a63a18638d43b93017dbb591b19c6d"
2177
  },
2178
  "hf_model_docs_data": {
2179
  "path": "hf_model:docs/data/task_method_20_gap_audit.json",
2180
  "exists": true,
2181
- "bytes": 52867,
2182
- "sha256": "255ba3324994ee1848a99f6bc08b74b447a63a18638d43b93017dbb591b19c6d"
2183
  },
2184
  "hf_model": {
2185
  "path": "hf_model:metrics/task_method_20_gap_audit.json",
2186
  "exists": true,
2187
- "bytes": 52867,
2188
- "sha256": "255ba3324994ee1848a99f6bc08b74b447a63a18638d43b93017dbb591b19c6d"
2189
  }
2190
  },
2191
  "failures": []
@@ -2245,45 +2245,45 @@
2245
  "local": {
2246
  "path": "repo:docs/data/unified_task_model_radar.json",
2247
  "exists": true,
2248
- "bytes": 231127,
2249
- "sha256": "3bcabe4b7182b66292c012f26401d753f581d9feb3d0adb312a5115933f34767"
2250
  },
2251
  "mirrors": {
2252
  "hf_space": {
2253
  "path": "hf_space:data/unified_task_model_radar.json",
2254
  "exists": true,
2255
- "bytes": 231127,
2256
- "sha256": "3bcabe4b7182b66292c012f26401d753f581d9feb3d0adb312a5115933f34767"
2257
  },
2258
  "hf_artifacts_data": {
2259
  "path": "hf_artifacts:data/unified_task_model_radar.json",
2260
  "exists": true,
2261
- "bytes": 231127,
2262
- "sha256": "3bcabe4b7182b66292c012f26401d753f581d9feb3d0adb312a5115933f34767"
2263
  },
2264
  "hf_artifacts": {
2265
  "path": "hf_artifacts:docs/data/unified_task_model_radar.json",
2266
  "exists": true,
2267
- "bytes": 231127,
2268
- "sha256": "3bcabe4b7182b66292c012f26401d753f581d9feb3d0adb312a5115933f34767"
2269
  },
2270
  "hf_model_data": {
2271
  "path": "hf_model:data/unified_task_model_radar.json",
2272
  "exists": true,
2273
- "bytes": 231127,
2274
- "sha256": "3bcabe4b7182b66292c012f26401d753f581d9feb3d0adb312a5115933f34767"
2275
  },
2276
  "hf_model_docs_data": {
2277
  "path": "hf_model:docs/data/unified_task_model_radar.json",
2278
  "exists": true,
2279
- "bytes": 231127,
2280
- "sha256": "3bcabe4b7182b66292c012f26401d753f581d9feb3d0adb312a5115933f34767"
2281
  },
2282
  "hf_model": {
2283
  "path": "hf_model:metrics/unified_task_model_radar.json",
2284
  "exists": true,
2285
- "bytes": 231127,
2286
- "sha256": "3bcabe4b7182b66292c012f26401d753f581d9feb3d0adb312a5115933f34767"
2287
  }
2288
  },
2289
  "failures": []
@@ -2295,44 +2295,44 @@
2295
  "path": "repo:docs/data/website_integrity.json",
2296
  "exists": true,
2297
  "bytes": 20021,
2298
- "sha256": "1efe3b5b4a3d0a148df2dea58001a6d6aa9ea1d8c176fe647c056d7cbd676797"
2299
  },
2300
  "mirrors": {
2301
  "hf_space": {
2302
  "path": "hf_space:data/website_integrity.json",
2303
  "exists": true,
2304
  "bytes": 20021,
2305
- "sha256": "1efe3b5b4a3d0a148df2dea58001a6d6aa9ea1d8c176fe647c056d7cbd676797"
2306
  },
2307
  "hf_artifacts_data": {
2308
  "path": "hf_artifacts:data/website_integrity.json",
2309
  "exists": true,
2310
  "bytes": 20021,
2311
- "sha256": "1efe3b5b4a3d0a148df2dea58001a6d6aa9ea1d8c176fe647c056d7cbd676797"
2312
  },
2313
  "hf_artifacts": {
2314
  "path": "hf_artifacts:docs/data/website_integrity.json",
2315
  "exists": true,
2316
  "bytes": 20021,
2317
- "sha256": "1efe3b5b4a3d0a148df2dea58001a6d6aa9ea1d8c176fe647c056d7cbd676797"
2318
  },
2319
  "hf_model_data": {
2320
  "path": "hf_model:data/website_integrity.json",
2321
  "exists": true,
2322
  "bytes": 20021,
2323
- "sha256": "1efe3b5b4a3d0a148df2dea58001a6d6aa9ea1d8c176fe647c056d7cbd676797"
2324
  },
2325
  "hf_model_docs_data": {
2326
  "path": "hf_model:docs/data/website_integrity.json",
2327
  "exists": true,
2328
  "bytes": 20021,
2329
- "sha256": "1efe3b5b4a3d0a148df2dea58001a6d6aa9ea1d8c176fe647c056d7cbd676797"
2330
  },
2331
  "hf_model": {
2332
  "path": "hf_model:metrics/website_integrity.json",
2333
  "exists": true,
2334
  "bytes": 20021,
2335
- "sha256": "1efe3b5b4a3d0a148df2dea58001a6d6aa9ea1d8c176fe647c056d7cbd676797"
2336
  }
2337
  },
2338
  "failures": []
@@ -2515,33 +2515,33 @@
2515
  "local": {
2516
  "path": "repo:docs/assets/charts/episode128_task_model_radar.svg",
2517
  "exists": true,
2518
- "bytes": 44490,
2519
- "sha256": "537c0dc2f1173bc40aaa216cbf760aeea30c9325ddd5c08e1f16e476d4c01bdd"
2520
  },
2521
  "mirrors": {
2522
  "hf_space": {
2523
  "path": "hf_space:assets/charts/episode128_task_model_radar.svg",
2524
  "exists": true,
2525
- "bytes": 44490,
2526
- "sha256": "537c0dc2f1173bc40aaa216cbf760aeea30c9325ddd5c08e1f16e476d4c01bdd"
2527
  },
2528
  "hf_artifacts_docs": {
2529
  "path": "hf_artifacts:docs/assets/charts/episode128_task_model_radar.svg",
2530
  "exists": true,
2531
- "bytes": 44490,
2532
- "sha256": "537c0dc2f1173bc40aaa216cbf760aeea30c9325ddd5c08e1f16e476d4c01bdd"
2533
  },
2534
  "hf_artifacts_card": {
2535
  "path": "hf_artifacts:assets/charts/episode128_task_model_radar.svg",
2536
  "exists": true,
2537
- "bytes": 44490,
2538
- "sha256": "537c0dc2f1173bc40aaa216cbf760aeea30c9325ddd5c08e1f16e476d4c01bdd"
2539
  },
2540
  "hf_model": {
2541
  "path": "hf_model:assets/charts/episode128_task_model_radar.svg",
2542
  "exists": true,
2543
- "bytes": 44490,
2544
- "sha256": "537c0dc2f1173bc40aaa216cbf760aeea30c9325ddd5c08e1f16e476d4c01bdd"
2545
  }
2546
  },
2547
  "failures": []
@@ -2589,33 +2589,33 @@
2589
  "local": {
2590
  "path": "repo:docs/assets/charts/unified_task_model_radar.svg",
2591
  "exists": true,
2592
- "bytes": 50506,
2593
- "sha256": "890cbddb57e241e4360c96c18a013c98ed56d26711f136babac6e3313751bbfb"
2594
  },
2595
  "mirrors": {
2596
  "hf_space": {
2597
  "path": "hf_space:assets/charts/unified_task_model_radar.svg",
2598
  "exists": true,
2599
- "bytes": 50506,
2600
- "sha256": "890cbddb57e241e4360c96c18a013c98ed56d26711f136babac6e3313751bbfb"
2601
  },
2602
  "hf_artifacts_docs": {
2603
  "path": "hf_artifacts:docs/assets/charts/unified_task_model_radar.svg",
2604
  "exists": true,
2605
- "bytes": 50506,
2606
- "sha256": "890cbddb57e241e4360c96c18a013c98ed56d26711f136babac6e3313751bbfb"
2607
  },
2608
  "hf_artifacts_card": {
2609
  "path": "hf_artifacts:assets/charts/unified_task_model_radar.svg",
2610
  "exists": true,
2611
- "bytes": 50506,
2612
- "sha256": "890cbddb57e241e4360c96c18a013c98ed56d26711f136babac6e3313751bbfb"
2613
  },
2614
  "hf_model": {
2615
  "path": "hf_model:assets/charts/unified_task_model_radar.svg",
2616
  "exists": true,
2617
- "bytes": 50506,
2618
- "sha256": "890cbddb57e241e4360c96c18a013c98ed56d26711f136babac6e3313751bbfb"
2619
  }
2620
  },
2621
  "failures": []
@@ -3917,6 +3917,31 @@
3917
  },
3918
  "failures": []
3919
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3920
  {
3921
  "name": "scripts/omni/collect_qwen3_v4_release_artifacts.py",
3922
  "status": "pass",
@@ -4973,21 +4998,21 @@
4973
  "local": {
4974
  "path": "repo:scripts/validate_mirror_parity.py",
4975
  "exists": true,
4976
- "bytes": 28427,
4977
- "sha256": "a85b031f81f378c6baa2a4201589383f828934f03b74ba300eb0bc803c929801"
4978
  },
4979
  "mirrors": {
4980
  "hf_artifacts": {
4981
  "path": "hf_artifacts:scripts/validate_mirror_parity.py",
4982
  "exists": true,
4983
- "bytes": 28427,
4984
- "sha256": "a85b031f81f378c6baa2a4201589383f828934f03b74ba300eb0bc803c929801"
4985
  },
4986
  "hf_model": {
4987
  "path": "hf_model:scripts/validate_mirror_parity.py",
4988
  "exists": true,
4989
- "bytes": 28427,
4990
- "sha256": "a85b031f81f378c6baa2a4201589383f828934f03b74ba300eb0bc803c929801"
4991
  }
4992
  },
4993
  "failures": []
@@ -4998,21 +5023,21 @@
4998
  "local": {
4999
  "path": "repo:scripts/validate_publication_package.py",
5000
  "exists": true,
5001
- "bytes": 19912,
5002
- "sha256": "efb862566bedc49b0eaa11c9abdeb29abf8d3acd461b772fc79854e24dcb1c18"
5003
  },
5004
  "mirrors": {
5005
  "hf_artifacts": {
5006
  "path": "hf_artifacts:scripts/validate_publication_package.py",
5007
  "exists": true,
5008
- "bytes": 19912,
5009
- "sha256": "efb862566bedc49b0eaa11c9abdeb29abf8d3acd461b772fc79854e24dcb1c18"
5010
  },
5011
  "hf_model": {
5012
  "path": "hf_model:scripts/validate_publication_package.py",
5013
  "exists": true,
5014
- "bytes": 19912,
5015
- "sha256": "efb862566bedc49b0eaa11c9abdeb29abf8d3acd461b772fc79854e24dcb1c18"
5016
  }
5017
  },
5018
  "failures": []
@@ -20782,27 +20807,27 @@
20782
  "local": {
20783
  "path": "repo:TASK_METHOD_20_GAP_AUDIT.md",
20784
  "exists": true,
20785
- "bytes": 14981,
20786
- "sha256": "90f9885e601b2f19af863650fae7821092147ada1d86bb945b08c3cd603197ac"
20787
  },
20788
  "mirrors": {
20789
  "hf_space": {
20790
  "path": "hf_space:TASK_METHOD_20_GAP_AUDIT.md",
20791
  "exists": true,
20792
- "bytes": 14981,
20793
- "sha256": "90f9885e601b2f19af863650fae7821092147ada1d86bb945b08c3cd603197ac"
20794
  },
20795
  "hf_artifacts": {
20796
  "path": "hf_artifacts:TASK_METHOD_20_GAP_AUDIT.md",
20797
  "exists": true,
20798
- "bytes": 14981,
20799
- "sha256": "90f9885e601b2f19af863650fae7821092147ada1d86bb945b08c3cd603197ac"
20800
  },
20801
  "hf_model": {
20802
  "path": "hf_model:TASK_METHOD_20_GAP_AUDIT.md",
20803
  "exists": true,
20804
- "bytes": 14981,
20805
- "sha256": "90f9885e601b2f19af863650fae7821092147ada1d86bb945b08c3cd603197ac"
20806
  }
20807
  },
20808
  "failures": []
@@ -20813,27 +20838,27 @@
20813
  "local": {
20814
  "path": "repo:TASK_METHOD_20_RESULT_MATRIX.md",
20815
  "exists": true,
20816
- "bytes": 4152,
20817
- "sha256": "c5ce3d4dc21751dc0b7e371ac0d92790190e306f48b0147d99952646ae2dedb1"
20818
  },
20819
  "mirrors": {
20820
  "hf_space": {
20821
  "path": "hf_space:TASK_METHOD_20_RESULT_MATRIX.md",
20822
  "exists": true,
20823
- "bytes": 4152,
20824
- "sha256": "c5ce3d4dc21751dc0b7e371ac0d92790190e306f48b0147d99952646ae2dedb1"
20825
  },
20826
  "hf_artifacts": {
20827
  "path": "hf_artifacts:TASK_METHOD_20_RESULT_MATRIX.md",
20828
  "exists": true,
20829
- "bytes": 4152,
20830
- "sha256": "c5ce3d4dc21751dc0b7e371ac0d92790190e306f48b0147d99952646ae2dedb1"
20831
  },
20832
  "hf_model": {
20833
  "path": "hf_model:TASK_METHOD_20_RESULT_MATRIX.md",
20834
  "exists": true,
20835
- "bytes": 4152,
20836
- "sha256": "c5ce3d4dc21751dc0b7e371ac0d92790190e306f48b0147d99952646ae2dedb1"
20837
  }
20838
  },
20839
  "failures": []
 
1
  {
2
  "status": "pass",
3
+ "generated_at_utc": "2026-06-18T10:05:53+00:00",
4
  "hf_root": "hf_publish",
5
  "summary": {
6
+ "group_count": 650,
7
  "failure_count": 0,
8
  "failures_by_surface": {}
9
  },
 
139
  "path": "repo:docs/data/artifact_index.json",
140
  "exists": true,
141
  "bytes": 116109,
142
+ "sha256": "b88adcd80deb8cc4b4c3ed08e1a9ee7c2d8cdb21feab8a3494bd2e80e67d1b9a"
143
  },
144
  "mirrors": {
145
  "hf_space": {
146
  "path": "hf_space:data/artifact_index.json",
147
  "exists": true,
148
  "bytes": 116109,
149
+ "sha256": "b88adcd80deb8cc4b4c3ed08e1a9ee7c2d8cdb21feab8a3494bd2e80e67d1b9a"
150
  },
151
  "hf_artifacts_data": {
152
  "path": "hf_artifacts:data/artifact_index.json",
153
  "exists": true,
154
  "bytes": 116109,
155
+ "sha256": "b88adcd80deb8cc4b4c3ed08e1a9ee7c2d8cdb21feab8a3494bd2e80e67d1b9a"
156
  },
157
  "hf_artifacts": {
158
  "path": "hf_artifacts:docs/data/artifact_index.json",
159
  "exists": true,
160
  "bytes": 116109,
161
+ "sha256": "b88adcd80deb8cc4b4c3ed08e1a9ee7c2d8cdb21feab8a3494bd2e80e67d1b9a"
162
  },
163
  "hf_model_data": {
164
  "path": "hf_model:data/artifact_index.json",
165
  "exists": true,
166
  "bytes": 116109,
167
+ "sha256": "b88adcd80deb8cc4b4c3ed08e1a9ee7c2d8cdb21feab8a3494bd2e80e67d1b9a"
168
  },
169
  "hf_model_docs_data": {
170
  "path": "hf_model:docs/data/artifact_index.json",
171
  "exists": true,
172
  "bytes": 116109,
173
+ "sha256": "b88adcd80deb8cc4b4c3ed08e1a9ee7c2d8cdb21feab8a3494bd2e80e67d1b9a"
174
  },
175
  "hf_model": {
176
  "path": "hf_model:metrics/artifact_index.json",
177
  "exists": true,
178
  "bytes": 116109,
179
+ "sha256": "b88adcd80deb8cc4b4c3ed08e1a9ee7c2d8cdb21feab8a3494bd2e80e67d1b9a"
180
  }
181
  },
182
  "failures": []
 
335
  "path": "repo:docs/data/figure_index.json",
336
  "exists": true,
337
  "bytes": 19441,
338
+ "sha256": "ec004dfdba639132e975c65c8a524e45caa246b9d03baa1ea26eca2b288186ff"
339
  },
340
  "mirrors": {
341
  "hf_space": {
342
  "path": "hf_space:data/figure_index.json",
343
  "exists": true,
344
  "bytes": 19441,
345
+ "sha256": "ec004dfdba639132e975c65c8a524e45caa246b9d03baa1ea26eca2b288186ff"
346
  },
347
  "hf_artifacts_data": {
348
  "path": "hf_artifacts:data/figure_index.json",
349
  "exists": true,
350
  "bytes": 19441,
351
+ "sha256": "ec004dfdba639132e975c65c8a524e45caa246b9d03baa1ea26eca2b288186ff"
352
  },
353
  "hf_artifacts": {
354
  "path": "hf_artifacts:docs/data/figure_index.json",
355
  "exists": true,
356
  "bytes": 19441,
357
+ "sha256": "ec004dfdba639132e975c65c8a524e45caa246b9d03baa1ea26eca2b288186ff"
358
  },
359
  "hf_model_data": {
360
  "path": "hf_model:data/figure_index.json",
361
  "exists": true,
362
  "bytes": 19441,
363
+ "sha256": "ec004dfdba639132e975c65c8a524e45caa246b9d03baa1ea26eca2b288186ff"
364
  },
365
  "hf_model_docs_data": {
366
  "path": "hf_model:docs/data/figure_index.json",
367
  "exists": true,
368
  "bytes": 19441,
369
+ "sha256": "ec004dfdba639132e975c65c8a524e45caa246b9d03baa1ea26eca2b288186ff"
370
  },
371
  "hf_model": {
372
  "path": "hf_model:metrics/figure_index.json",
373
  "exists": true,
374
  "bytes": 19441,
375
+ "sha256": "ec004dfdba639132e975c65c8a524e45caa246b9d03baa1ea26eca2b288186ff"
376
  }
377
  },
378
  "failures": []
 
922
  "local": {
923
  "path": "repo:docs/data/publication_audit.json",
924
  "exists": true,
925
+ "bytes": 9598,
926
+ "sha256": "f1d2bff3ff9bb0be059a23eec635974cdd8208a8670277178050c47e1f8b805a"
927
  },
928
  "mirrors": {
929
  "hf_space": {
930
  "path": "hf_space:data/publication_audit.json",
931
  "exists": true,
932
+ "bytes": 9598,
933
+ "sha256": "f1d2bff3ff9bb0be059a23eec635974cdd8208a8670277178050c47e1f8b805a"
934
  },
935
  "hf_artifacts_data": {
936
  "path": "hf_artifacts:data/publication_audit.json",
937
  "exists": true,
938
+ "bytes": 9598,
939
+ "sha256": "f1d2bff3ff9bb0be059a23eec635974cdd8208a8670277178050c47e1f8b805a"
940
  },
941
  "hf_artifacts": {
942
  "path": "hf_artifacts:docs/data/publication_audit.json",
943
  "exists": true,
944
+ "bytes": 9598,
945
+ "sha256": "f1d2bff3ff9bb0be059a23eec635974cdd8208a8670277178050c47e1f8b805a"
946
  },
947
  "hf_model_data": {
948
  "path": "hf_model:data/publication_audit.json",
949
  "exists": true,
950
+ "bytes": 9598,
951
+ "sha256": "f1d2bff3ff9bb0be059a23eec635974cdd8208a8670277178050c47e1f8b805a"
952
  },
953
  "hf_model_docs_data": {
954
  "path": "hf_model:docs/data/publication_audit.json",
955
  "exists": true,
956
+ "bytes": 9598,
957
+ "sha256": "f1d2bff3ff9bb0be059a23eec635974cdd8208a8670277178050c47e1f8b805a"
958
  },
959
  "hf_model": {
960
  "path": "hf_model:metrics/publication_audit.json",
961
  "exists": true,
962
+ "bytes": 9598,
963
+ "sha256": "f1d2bff3ff9bb0be059a23eec635974cdd8208a8670277178050c47e1f8b805a"
964
  }
965
  },
966
  "failures": []
 
972
  "path": "repo:docs/data/public_surface_qa.json",
973
  "exists": true,
974
  "bytes": 7126,
975
+ "sha256": "a31696958f45455e18b6d85c5b206e19746e3948781c04bde1cf9e3f4c9ba108"
976
  },
977
  "mirrors": {
978
  "hf_space": {
979
  "path": "hf_space:data/public_surface_qa.json",
980
  "exists": true,
981
  "bytes": 7126,
982
+ "sha256": "a31696958f45455e18b6d85c5b206e19746e3948781c04bde1cf9e3f4c9ba108"
983
  },
984
  "hf_artifacts_data": {
985
  "path": "hf_artifacts:data/public_surface_qa.json",
986
  "exists": true,
987
  "bytes": 7126,
988
+ "sha256": "a31696958f45455e18b6d85c5b206e19746e3948781c04bde1cf9e3f4c9ba108"
989
  },
990
  "hf_artifacts": {
991
  "path": "hf_artifacts:docs/data/public_surface_qa.json",
992
  "exists": true,
993
  "bytes": 7126,
994
+ "sha256": "a31696958f45455e18b6d85c5b206e19746e3948781c04bde1cf9e3f4c9ba108"
995
  },
996
  "hf_model_data": {
997
  "path": "hf_model:data/public_surface_qa.json",
998
  "exists": true,
999
  "bytes": 7126,
1000
+ "sha256": "a31696958f45455e18b6d85c5b206e19746e3948781c04bde1cf9e3f4c9ba108"
1001
  },
1002
  "hf_model_docs_data": {
1003
  "path": "hf_model:docs/data/public_surface_qa.json",
1004
  "exists": true,
1005
  "bytes": 7126,
1006
+ "sha256": "a31696958f45455e18b6d85c5b206e19746e3948781c04bde1cf9e3f4c9ba108"
1007
  },
1008
  "hf_model": {
1009
  "path": "hf_model:metrics/public_surface_qa.json",
1010
  "exists": true,
1011
  "bytes": 7126,
1012
+ "sha256": "a31696958f45455e18b6d85c5b206e19746e3948781c04bde1cf9e3f4c9ba108"
1013
  }
1014
  },
1015
  "failures": []
 
1119
  "path": "repo:docs/data/quality_gates.json",
1120
  "exists": true,
1121
  "bytes": 8100,
1122
+ "sha256": "0ebf0a5e182beac55d7eddf9497cede3fa311d53d0244d39cedf912a01dd958e"
1123
  },
1124
  "mirrors": {
1125
  "hf_space": {
1126
  "path": "hf_space:data/quality_gates.json",
1127
  "exists": true,
1128
  "bytes": 8100,
1129
+ "sha256": "0ebf0a5e182beac55d7eddf9497cede3fa311d53d0244d39cedf912a01dd958e"
1130
  },
1131
  "hf_artifacts_data": {
1132
  "path": "hf_artifacts:data/quality_gates.json",
1133
  "exists": true,
1134
  "bytes": 8100,
1135
+ "sha256": "0ebf0a5e182beac55d7eddf9497cede3fa311d53d0244d39cedf912a01dd958e"
1136
  },
1137
  "hf_artifacts": {
1138
  "path": "hf_artifacts:docs/data/quality_gates.json",
1139
  "exists": true,
1140
  "bytes": 8100,
1141
+ "sha256": "0ebf0a5e182beac55d7eddf9497cede3fa311d53d0244d39cedf912a01dd958e"
1142
  },
1143
  "hf_model_data": {
1144
  "path": "hf_model:data/quality_gates.json",
1145
  "exists": true,
1146
  "bytes": 8100,
1147
+ "sha256": "0ebf0a5e182beac55d7eddf9497cede3fa311d53d0244d39cedf912a01dd958e"
1148
  },
1149
  "hf_model_docs_data": {
1150
  "path": "hf_model:docs/data/quality_gates.json",
1151
  "exists": true,
1152
  "bytes": 8100,
1153
+ "sha256": "0ebf0a5e182beac55d7eddf9497cede3fa311d53d0244d39cedf912a01dd958e"
1154
  },
1155
  "hf_model": {
1156
  "path": "hf_model:metrics/quality_gates.json",
1157
  "exists": true,
1158
  "bytes": 8100,
1159
+ "sha256": "0ebf0a5e182beac55d7eddf9497cede3fa311d53d0244d39cedf912a01dd958e"
1160
  }
1161
  },
1162
  "failures": []
 
1560
  "path": "repo:docs/data/scope_claims_audit.json",
1561
  "exists": true,
1562
  "bytes": 21630,
1563
+ "sha256": "ad761be4cf4410d2a18f8af08eb742d37661f1ff2eb78ea60d8d74c1fcf45a1a"
1564
  },
1565
  "mirrors": {
1566
  "hf_space": {
1567
  "path": "hf_space:data/scope_claims_audit.json",
1568
  "exists": true,
1569
  "bytes": 21630,
1570
+ "sha256": "ad761be4cf4410d2a18f8af08eb742d37661f1ff2eb78ea60d8d74c1fcf45a1a"
1571
  },
1572
  "hf_artifacts_data": {
1573
  "path": "hf_artifacts:data/scope_claims_audit.json",
1574
  "exists": true,
1575
  "bytes": 21630,
1576
+ "sha256": "ad761be4cf4410d2a18f8af08eb742d37661f1ff2eb78ea60d8d74c1fcf45a1a"
1577
  },
1578
  "hf_artifacts": {
1579
  "path": "hf_artifacts:docs/data/scope_claims_audit.json",
1580
  "exists": true,
1581
  "bytes": 21630,
1582
+ "sha256": "ad761be4cf4410d2a18f8af08eb742d37661f1ff2eb78ea60d8d74c1fcf45a1a"
1583
  },
1584
  "hf_model_data": {
1585
  "path": "hf_model:data/scope_claims_audit.json",
1586
  "exists": true,
1587
  "bytes": 21630,
1588
+ "sha256": "ad761be4cf4410d2a18f8af08eb742d37661f1ff2eb78ea60d8d74c1fcf45a1a"
1589
  },
1590
  "hf_model_docs_data": {
1591
  "path": "hf_model:docs/data/scope_claims_audit.json",
1592
  "exists": true,
1593
  "bytes": 21630,
1594
+ "sha256": "ad761be4cf4410d2a18f8af08eb742d37661f1ff2eb78ea60d8d74c1fcf45a1a"
1595
  },
1596
  "hf_model": {
1597
  "path": "hf_model:metrics/scope_claims_audit.json",
1598
  "exists": true,
1599
  "bytes": 21630,
1600
+ "sha256": "ad761be4cf4410d2a18f8af08eb742d37661f1ff2eb78ea60d8d74c1fcf45a1a"
1601
  }
1602
  },
1603
  "failures": []
 
1658
  "path": "repo:docs/data/source_alignment_audit.json",
1659
  "exists": true,
1660
  "bytes": 4432,
1661
+ "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
1662
  },
1663
  "mirrors": {
1664
  "hf_space": {
1665
  "path": "hf_space:data/source_alignment_audit.json",
1666
  "exists": true,
1667
  "bytes": 4432,
1668
+ "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
1669
  },
1670
  "hf_artifacts_data": {
1671
  "path": "hf_artifacts:data/source_alignment_audit.json",
1672
  "exists": true,
1673
  "bytes": 4432,
1674
+ "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
1675
  },
1676
  "hf_artifacts": {
1677
  "path": "hf_artifacts:docs/data/source_alignment_audit.json",
1678
  "exists": true,
1679
  "bytes": 4432,
1680
+ "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
1681
  },
1682
  "hf_model_data": {
1683
  "path": "hf_model:data/source_alignment_audit.json",
1684
  "exists": true,
1685
  "bytes": 4432,
1686
+ "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
1687
  },
1688
  "hf_model_docs_data": {
1689
  "path": "hf_model:docs/data/source_alignment_audit.json",
1690
  "exists": true,
1691
  "bytes": 4432,
1692
+ "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
1693
  },
1694
  "hf_model": {
1695
  "path": "hf_model:metrics/source_alignment_audit.json",
1696
  "exists": true,
1697
  "bytes": 4432,
1698
+ "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
1699
  }
1700
  },
1701
  "failures": []
 
1756
  "path": "repo:docs/data/single_episode_task_model_radar.json",
1757
  "exists": true,
1758
  "bytes": 50973,
1759
+ "sha256": "6db28943d1206aef75fbce8ea87ea52a35c0144c6186214f37da9311ca8c9a0c"
1760
  },
1761
  "mirrors": {
1762
  "hf_space": {
1763
  "path": "hf_space:data/single_episode_task_model_radar.json",
1764
  "exists": true,
1765
  "bytes": 50973,
1766
+ "sha256": "6db28943d1206aef75fbce8ea87ea52a35c0144c6186214f37da9311ca8c9a0c"
1767
  },
1768
  "hf_artifacts_data": {
1769
  "path": "hf_artifacts:data/single_episode_task_model_radar.json",
1770
  "exists": true,
1771
  "bytes": 50973,
1772
+ "sha256": "6db28943d1206aef75fbce8ea87ea52a35c0144c6186214f37da9311ca8c9a0c"
1773
  },
1774
  "hf_artifacts": {
1775
  "path": "hf_artifacts:docs/data/single_episode_task_model_radar.json",
1776
  "exists": true,
1777
  "bytes": 50973,
1778
+ "sha256": "6db28943d1206aef75fbce8ea87ea52a35c0144c6186214f37da9311ca8c9a0c"
1779
  },
1780
  "hf_model_data": {
1781
  "path": "hf_model:data/single_episode_task_model_radar.json",
1782
  "exists": true,
1783
  "bytes": 50973,
1784
+ "sha256": "6db28943d1206aef75fbce8ea87ea52a35c0144c6186214f37da9311ca8c9a0c"
1785
  },
1786
  "hf_model_docs_data": {
1787
  "path": "hf_model:docs/data/single_episode_task_model_radar.json",
1788
  "exists": true,
1789
  "bytes": 50973,
1790
+ "sha256": "6db28943d1206aef75fbce8ea87ea52a35c0144c6186214f37da9311ca8c9a0c"
1791
  },
1792
  "hf_model": {
1793
  "path": "hf_model:metrics/single_episode_task_model_radar.json",
1794
  "exists": true,
1795
  "bytes": 50973,
1796
+ "sha256": "6db28943d1206aef75fbce8ea87ea52a35c0144c6186214f37da9311ca8c9a0c"
1797
  }
1798
  },
1799
  "failures": []
 
1804
  "local": {
1805
  "path": "repo:docs/data/episode128_task_model_radar.json",
1806
  "exists": true,
1807
+ "bytes": 187271,
1808
+ "sha256": "acd8623ad19bf0d0ee1ffb434ecefa087339b59e97d30809eca9b739f83f1a89"
1809
  },
1810
  "mirrors": {
1811
  "hf_space": {
1812
  "path": "hf_space:data/episode128_task_model_radar.json",
1813
  "exists": true,
1814
+ "bytes": 187271,
1815
+ "sha256": "acd8623ad19bf0d0ee1ffb434ecefa087339b59e97d30809eca9b739f83f1a89"
1816
  },
1817
  "hf_artifacts_data": {
1818
  "path": "hf_artifacts:data/episode128_task_model_radar.json",
1819
  "exists": true,
1820
+ "bytes": 187271,
1821
+ "sha256": "acd8623ad19bf0d0ee1ffb434ecefa087339b59e97d30809eca9b739f83f1a89"
1822
  },
1823
  "hf_artifacts": {
1824
  "path": "hf_artifacts:docs/data/episode128_task_model_radar.json",
1825
  "exists": true,
1826
+ "bytes": 187271,
1827
+ "sha256": "acd8623ad19bf0d0ee1ffb434ecefa087339b59e97d30809eca9b739f83f1a89"
1828
  },
1829
  "hf_model_data": {
1830
  "path": "hf_model:data/episode128_task_model_radar.json",
1831
  "exists": true,
1832
+ "bytes": 187271,
1833
+ "sha256": "acd8623ad19bf0d0ee1ffb434ecefa087339b59e97d30809eca9b739f83f1a89"
1834
  },
1835
  "hf_model_docs_data": {
1836
  "path": "hf_model:docs/data/episode128_task_model_radar.json",
1837
  "exists": true,
1838
+ "bytes": 187271,
1839
+ "sha256": "acd8623ad19bf0d0ee1ffb434ecefa087339b59e97d30809eca9b739f83f1a89"
1840
  },
1841
  "hf_model": {
1842
  "path": "hf_model:metrics/episode128_task_model_radar.json",
1843
  "exists": true,
1844
+ "bytes": 187271,
1845
+ "sha256": "acd8623ad19bf0d0ee1ffb434ecefa087339b59e97d30809eca9b739f83f1a89"
1846
  }
1847
  },
1848
  "failures": []
 
2001
  "path": "repo:docs/data/task_surface_integrity.json",
2002
  "exists": true,
2003
  "bytes": 45779,
2004
+ "sha256": "0179ae9e9f4dffe7fea263b0e5a7a9b8c930bfcdf5794ff42c46f65efeee3182"
2005
  },
2006
  "mirrors": {
2007
  "hf_space": {
2008
  "path": "hf_space:data/task_surface_integrity.json",
2009
  "exists": true,
2010
  "bytes": 45779,
2011
+ "sha256": "0179ae9e9f4dffe7fea263b0e5a7a9b8c930bfcdf5794ff42c46f65efeee3182"
2012
  },
2013
  "hf_artifacts_data": {
2014
  "path": "hf_artifacts:data/task_surface_integrity.json",
2015
  "exists": true,
2016
  "bytes": 45779,
2017
+ "sha256": "0179ae9e9f4dffe7fea263b0e5a7a9b8c930bfcdf5794ff42c46f65efeee3182"
2018
  },
2019
  "hf_artifacts": {
2020
  "path": "hf_artifacts:docs/data/task_surface_integrity.json",
2021
  "exists": true,
2022
  "bytes": 45779,
2023
+ "sha256": "0179ae9e9f4dffe7fea263b0e5a7a9b8c930bfcdf5794ff42c46f65efeee3182"
2024
  },
2025
  "hf_model_data": {
2026
  "path": "hf_model:data/task_surface_integrity.json",
2027
  "exists": true,
2028
  "bytes": 45779,
2029
+ "sha256": "0179ae9e9f4dffe7fea263b0e5a7a9b8c930bfcdf5794ff42c46f65efeee3182"
2030
  },
2031
  "hf_model_docs_data": {
2032
  "path": "hf_model:docs/data/task_surface_integrity.json",
2033
  "exists": true,
2034
  "bytes": 45779,
2035
+ "sha256": "0179ae9e9f4dffe7fea263b0e5a7a9b8c930bfcdf5794ff42c46f65efeee3182"
2036
  },
2037
  "hf_model": {
2038
  "path": "hf_model:metrics/task_surface_integrity.json",
2039
  "exists": true,
2040
  "bytes": 45779,
2041
+ "sha256": "0179ae9e9f4dffe7fea263b0e5a7a9b8c930bfcdf5794ff42c46f65efeee3182"
2042
  }
2043
  },
2044
  "failures": []
 
2098
  "local": {
2099
  "path": "repo:docs/data/task_method_20_result_matrix.json",
2100
  "exists": true,
2101
+ "bytes": 129687,
2102
+ "sha256": "e5d3fa22013fedf350907746f775cc4a1ca3bb3f816b40ca9467d51cf16925f8"
2103
  },
2104
  "mirrors": {
2105
  "hf_space": {
2106
  "path": "hf_space:data/task_method_20_result_matrix.json",
2107
  "exists": true,
2108
+ "bytes": 129687,
2109
+ "sha256": "e5d3fa22013fedf350907746f775cc4a1ca3bb3f816b40ca9467d51cf16925f8"
2110
  },
2111
  "hf_artifacts_data": {
2112
  "path": "hf_artifacts:data/task_method_20_result_matrix.json",
2113
  "exists": true,
2114
+ "bytes": 129687,
2115
+ "sha256": "e5d3fa22013fedf350907746f775cc4a1ca3bb3f816b40ca9467d51cf16925f8"
2116
  },
2117
  "hf_artifacts": {
2118
  "path": "hf_artifacts:docs/data/task_method_20_result_matrix.json",
2119
  "exists": true,
2120
+ "bytes": 129687,
2121
+ "sha256": "e5d3fa22013fedf350907746f775cc4a1ca3bb3f816b40ca9467d51cf16925f8"
2122
  },
2123
  "hf_model_data": {
2124
  "path": "hf_model:data/task_method_20_result_matrix.json",
2125
  "exists": true,
2126
+ "bytes": 129687,
2127
+ "sha256": "e5d3fa22013fedf350907746f775cc4a1ca3bb3f816b40ca9467d51cf16925f8"
2128
  },
2129
  "hf_model_docs_data": {
2130
  "path": "hf_model:docs/data/task_method_20_result_matrix.json",
2131
  "exists": true,
2132
+ "bytes": 129687,
2133
+ "sha256": "e5d3fa22013fedf350907746f775cc4a1ca3bb3f816b40ca9467d51cf16925f8"
2134
  },
2135
  "hf_model": {
2136
  "path": "hf_model:metrics/task_method_20_result_matrix.json",
2137
  "exists": true,
2138
+ "bytes": 129687,
2139
+ "sha256": "e5d3fa22013fedf350907746f775cc4a1ca3bb3f816b40ca9467d51cf16925f8"
2140
  }
2141
  },
2142
  "failures": []
 
2147
  "local": {
2148
  "path": "repo:docs/data/task_method_20_gap_audit.json",
2149
  "exists": true,
2150
+ "bytes": 52153,
2151
+ "sha256": "e47ac5d2ac8216f2b46b5fb868275c779226dce8089a8c025dd26571cb5758d3"
2152
  },
2153
  "mirrors": {
2154
  "hf_space": {
2155
  "path": "hf_space:data/task_method_20_gap_audit.json",
2156
  "exists": true,
2157
+ "bytes": 52153,
2158
+ "sha256": "e47ac5d2ac8216f2b46b5fb868275c779226dce8089a8c025dd26571cb5758d3"
2159
  },
2160
  "hf_artifacts_data": {
2161
  "path": "hf_artifacts:data/task_method_20_gap_audit.json",
2162
  "exists": true,
2163
+ "bytes": 52153,
2164
+ "sha256": "e47ac5d2ac8216f2b46b5fb868275c779226dce8089a8c025dd26571cb5758d3"
2165
  },
2166
  "hf_artifacts": {
2167
  "path": "hf_artifacts:docs/data/task_method_20_gap_audit.json",
2168
  "exists": true,
2169
+ "bytes": 52153,
2170
+ "sha256": "e47ac5d2ac8216f2b46b5fb868275c779226dce8089a8c025dd26571cb5758d3"
2171
  },
2172
  "hf_model_data": {
2173
  "path": "hf_model:data/task_method_20_gap_audit.json",
2174
  "exists": true,
2175
+ "bytes": 52153,
2176
+ "sha256": "e47ac5d2ac8216f2b46b5fb868275c779226dce8089a8c025dd26571cb5758d3"
2177
  },
2178
  "hf_model_docs_data": {
2179
  "path": "hf_model:docs/data/task_method_20_gap_audit.json",
2180
  "exists": true,
2181
+ "bytes": 52153,
2182
+ "sha256": "e47ac5d2ac8216f2b46b5fb868275c779226dce8089a8c025dd26571cb5758d3"
2183
  },
2184
  "hf_model": {
2185
  "path": "hf_model:metrics/task_method_20_gap_audit.json",
2186
  "exists": true,
2187
+ "bytes": 52153,
2188
+ "sha256": "e47ac5d2ac8216f2b46b5fb868275c779226dce8089a8c025dd26571cb5758d3"
2189
  }
2190
  },
2191
  "failures": []
 
2245
  "local": {
2246
  "path": "repo:docs/data/unified_task_model_radar.json",
2247
  "exists": true,
2248
+ "bytes": 231123,
2249
+ "sha256": "c004d35f0a3e0073c4116dd79a2bcdaac872605d715a7eccdaa15787df800f07"
2250
  },
2251
  "mirrors": {
2252
  "hf_space": {
2253
  "path": "hf_space:data/unified_task_model_radar.json",
2254
  "exists": true,
2255
+ "bytes": 231123,
2256
+ "sha256": "c004d35f0a3e0073c4116dd79a2bcdaac872605d715a7eccdaa15787df800f07"
2257
  },
2258
  "hf_artifacts_data": {
2259
  "path": "hf_artifacts:data/unified_task_model_radar.json",
2260
  "exists": true,
2261
+ "bytes": 231123,
2262
+ "sha256": "c004d35f0a3e0073c4116dd79a2bcdaac872605d715a7eccdaa15787df800f07"
2263
  },
2264
  "hf_artifacts": {
2265
  "path": "hf_artifacts:docs/data/unified_task_model_radar.json",
2266
  "exists": true,
2267
+ "bytes": 231123,
2268
+ "sha256": "c004d35f0a3e0073c4116dd79a2bcdaac872605d715a7eccdaa15787df800f07"
2269
  },
2270
  "hf_model_data": {
2271
  "path": "hf_model:data/unified_task_model_radar.json",
2272
  "exists": true,
2273
+ "bytes": 231123,
2274
+ "sha256": "c004d35f0a3e0073c4116dd79a2bcdaac872605d715a7eccdaa15787df800f07"
2275
  },
2276
  "hf_model_docs_data": {
2277
  "path": "hf_model:docs/data/unified_task_model_radar.json",
2278
  "exists": true,
2279
+ "bytes": 231123,
2280
+ "sha256": "c004d35f0a3e0073c4116dd79a2bcdaac872605d715a7eccdaa15787df800f07"
2281
  },
2282
  "hf_model": {
2283
  "path": "hf_model:metrics/unified_task_model_radar.json",
2284
  "exists": true,
2285
+ "bytes": 231123,
2286
+ "sha256": "c004d35f0a3e0073c4116dd79a2bcdaac872605d715a7eccdaa15787df800f07"
2287
  }
2288
  },
2289
  "failures": []
 
2295
  "path": "repo:docs/data/website_integrity.json",
2296
  "exists": true,
2297
  "bytes": 20021,
2298
+ "sha256": "ae1df93522b60a498309b3f5e9cc81b4dd1af7e761fab8a30261cb914c53de6d"
2299
  },
2300
  "mirrors": {
2301
  "hf_space": {
2302
  "path": "hf_space:data/website_integrity.json",
2303
  "exists": true,
2304
  "bytes": 20021,
2305
+ "sha256": "ae1df93522b60a498309b3f5e9cc81b4dd1af7e761fab8a30261cb914c53de6d"
2306
  },
2307
  "hf_artifacts_data": {
2308
  "path": "hf_artifacts:data/website_integrity.json",
2309
  "exists": true,
2310
  "bytes": 20021,
2311
+ "sha256": "ae1df93522b60a498309b3f5e9cc81b4dd1af7e761fab8a30261cb914c53de6d"
2312
  },
2313
  "hf_artifacts": {
2314
  "path": "hf_artifacts:docs/data/website_integrity.json",
2315
  "exists": true,
2316
  "bytes": 20021,
2317
+ "sha256": "ae1df93522b60a498309b3f5e9cc81b4dd1af7e761fab8a30261cb914c53de6d"
2318
  },
2319
  "hf_model_data": {
2320
  "path": "hf_model:data/website_integrity.json",
2321
  "exists": true,
2322
  "bytes": 20021,
2323
+ "sha256": "ae1df93522b60a498309b3f5e9cc81b4dd1af7e761fab8a30261cb914c53de6d"
2324
  },
2325
  "hf_model_docs_data": {
2326
  "path": "hf_model:docs/data/website_integrity.json",
2327
  "exists": true,
2328
  "bytes": 20021,
2329
+ "sha256": "ae1df93522b60a498309b3f5e9cc81b4dd1af7e761fab8a30261cb914c53de6d"
2330
  },
2331
  "hf_model": {
2332
  "path": "hf_model:metrics/website_integrity.json",
2333
  "exists": true,
2334
  "bytes": 20021,
2335
+ "sha256": "ae1df93522b60a498309b3f5e9cc81b4dd1af7e761fab8a30261cb914c53de6d"
2336
  }
2337
  },
2338
  "failures": []
 
2515
  "local": {
2516
  "path": "repo:docs/assets/charts/episode128_task_model_radar.svg",
2517
  "exists": true,
2518
+ "bytes": 44602,
2519
+ "sha256": "9a2fd542502cb26f093097d9ace238f8cf3b619e0abdec5bf2870c5271fb9ed5"
2520
  },
2521
  "mirrors": {
2522
  "hf_space": {
2523
  "path": "hf_space:assets/charts/episode128_task_model_radar.svg",
2524
  "exists": true,
2525
+ "bytes": 44602,
2526
+ "sha256": "9a2fd542502cb26f093097d9ace238f8cf3b619e0abdec5bf2870c5271fb9ed5"
2527
  },
2528
  "hf_artifacts_docs": {
2529
  "path": "hf_artifacts:docs/assets/charts/episode128_task_model_radar.svg",
2530
  "exists": true,
2531
+ "bytes": 44602,
2532
+ "sha256": "9a2fd542502cb26f093097d9ace238f8cf3b619e0abdec5bf2870c5271fb9ed5"
2533
  },
2534
  "hf_artifacts_card": {
2535
  "path": "hf_artifacts:assets/charts/episode128_task_model_radar.svg",
2536
  "exists": true,
2537
+ "bytes": 44602,
2538
+ "sha256": "9a2fd542502cb26f093097d9ace238f8cf3b619e0abdec5bf2870c5271fb9ed5"
2539
  },
2540
  "hf_model": {
2541
  "path": "hf_model:assets/charts/episode128_task_model_radar.svg",
2542
  "exists": true,
2543
+ "bytes": 44602,
2544
+ "sha256": "9a2fd542502cb26f093097d9ace238f8cf3b619e0abdec5bf2870c5271fb9ed5"
2545
  }
2546
  },
2547
  "failures": []
 
2589
  "local": {
2590
  "path": "repo:docs/assets/charts/unified_task_model_radar.svg",
2591
  "exists": true,
2592
+ "bytes": 50618,
2593
+ "sha256": "29ede875ef96c76a8aa7ec6e9883457be611fac8ef967b825041b33fe1d86863"
2594
  },
2595
  "mirrors": {
2596
  "hf_space": {
2597
  "path": "hf_space:assets/charts/unified_task_model_radar.svg",
2598
  "exists": true,
2599
+ "bytes": 50618,
2600
+ "sha256": "29ede875ef96c76a8aa7ec6e9883457be611fac8ef967b825041b33fe1d86863"
2601
  },
2602
  "hf_artifacts_docs": {
2603
  "path": "hf_artifacts:docs/assets/charts/unified_task_model_radar.svg",
2604
  "exists": true,
2605
+ "bytes": 50618,
2606
+ "sha256": "29ede875ef96c76a8aa7ec6e9883457be611fac8ef967b825041b33fe1d86863"
2607
  },
2608
  "hf_artifacts_card": {
2609
  "path": "hf_artifacts:assets/charts/unified_task_model_radar.svg",
2610
  "exists": true,
2611
+ "bytes": 50618,
2612
+ "sha256": "29ede875ef96c76a8aa7ec6e9883457be611fac8ef967b825041b33fe1d86863"
2613
  },
2614
  "hf_model": {
2615
  "path": "hf_model:assets/charts/unified_task_model_radar.svg",
2616
  "exists": true,
2617
+ "bytes": 50618,
2618
+ "sha256": "29ede875ef96c76a8aa7ec6e9883457be611fac8ef967b825041b33fe1d86863"
2619
  }
2620
  },
2621
  "failures": []
 
3917
  },
3918
  "failures": []
3919
  },
3920
+ {
3921
+ "name": "scripts/omni/collect_qwen3_retrieval_task_probe_results.sh",
3922
+ "status": "pass",
3923
+ "local": {
3924
+ "path": "repo:scripts/omni/collect_qwen3_retrieval_task_probe_results.sh",
3925
+ "exists": true,
3926
+ "bytes": 3435,
3927
+ "sha256": "257ba6267aab0ee2e06a03a9ad61175773948d039c6c5ce168471a800c1342fc"
3928
+ },
3929
+ "mirrors": {
3930
+ "hf_artifacts": {
3931
+ "path": "hf_artifacts:scripts/omni/collect_qwen3_retrieval_task_probe_results.sh",
3932
+ "exists": true,
3933
+ "bytes": 3435,
3934
+ "sha256": "257ba6267aab0ee2e06a03a9ad61175773948d039c6c5ce168471a800c1342fc"
3935
+ },
3936
+ "hf_model": {
3937
+ "path": "hf_model:scripts/omni/collect_qwen3_retrieval_task_probe_results.sh",
3938
+ "exists": true,
3939
+ "bytes": 3435,
3940
+ "sha256": "257ba6267aab0ee2e06a03a9ad61175773948d039c6c5ce168471a800c1342fc"
3941
+ }
3942
+ },
3943
+ "failures": []
3944
+ },
3945
  {
3946
  "name": "scripts/omni/collect_qwen3_v4_release_artifacts.py",
3947
  "status": "pass",
 
4998
  "local": {
4999
  "path": "repo:scripts/validate_mirror_parity.py",
5000
  "exists": true,
5001
+ "bytes": 28485,
5002
+ "sha256": "6c7fbcf2e7a22a71a547da7bb004cd662b6ba742cb8d049da1881928e9c6f509"
5003
  },
5004
  "mirrors": {
5005
  "hf_artifacts": {
5006
  "path": "hf_artifacts:scripts/validate_mirror_parity.py",
5007
  "exists": true,
5008
+ "bytes": 28485,
5009
+ "sha256": "6c7fbcf2e7a22a71a547da7bb004cd662b6ba742cb8d049da1881928e9c6f509"
5010
  },
5011
  "hf_model": {
5012
  "path": "hf_model:scripts/validate_mirror_parity.py",
5013
  "exists": true,
5014
+ "bytes": 28485,
5015
+ "sha256": "6c7fbcf2e7a22a71a547da7bb004cd662b6ba742cb8d049da1881928e9c6f509"
5016
  }
5017
  },
5018
  "failures": []
 
5023
  "local": {
5024
  "path": "repo:scripts/validate_publication_package.py",
5025
  "exists": true,
5026
+ "bytes": 19982,
5027
+ "sha256": "7770d277c8de2c8c93b92a135ce02c7c4dff64d15199f949688734c942f8fc45"
5028
  },
5029
  "mirrors": {
5030
  "hf_artifacts": {
5031
  "path": "hf_artifacts:scripts/validate_publication_package.py",
5032
  "exists": true,
5033
+ "bytes": 19982,
5034
+ "sha256": "7770d277c8de2c8c93b92a135ce02c7c4dff64d15199f949688734c942f8fc45"
5035
  },
5036
  "hf_model": {
5037
  "path": "hf_model:scripts/validate_publication_package.py",
5038
  "exists": true,
5039
+ "bytes": 19982,
5040
+ "sha256": "7770d277c8de2c8c93b92a135ce02c7c4dff64d15199f949688734c942f8fc45"
5041
  }
5042
  },
5043
  "failures": []
 
20807
  "local": {
20808
  "path": "repo:TASK_METHOD_20_GAP_AUDIT.md",
20809
  "exists": true,
20810
+ "bytes": 14812,
20811
+ "sha256": "d2f0228497fa834c7f097e1fe74e2210b85d0a01f7841356e67dc79929a74413"
20812
  },
20813
  "mirrors": {
20814
  "hf_space": {
20815
  "path": "hf_space:TASK_METHOD_20_GAP_AUDIT.md",
20816
  "exists": true,
20817
+ "bytes": 14812,
20818
+ "sha256": "d2f0228497fa834c7f097e1fe74e2210b85d0a01f7841356e67dc79929a74413"
20819
  },
20820
  "hf_artifacts": {
20821
  "path": "hf_artifacts:TASK_METHOD_20_GAP_AUDIT.md",
20822
  "exists": true,
20823
+ "bytes": 14812,
20824
+ "sha256": "d2f0228497fa834c7f097e1fe74e2210b85d0a01f7841356e67dc79929a74413"
20825
  },
20826
  "hf_model": {
20827
  "path": "hf_model:TASK_METHOD_20_GAP_AUDIT.md",
20828
  "exists": true,
20829
+ "bytes": 14812,
20830
+ "sha256": "d2f0228497fa834c7f097e1fe74e2210b85d0a01f7841356e67dc79929a74413"
20831
  }
20832
  },
20833
  "failures": []
 
20838
  "local": {
20839
  "path": "repo:TASK_METHOD_20_RESULT_MATRIX.md",
20840
  "exists": true,
20841
+ "bytes": 4144,
20842
+ "sha256": "dac2828ba0286bc35290a61b6d02dbd75f0b3acb8d47a73cfa7f072d7fa209c1"
20843
  },
20844
  "mirrors": {
20845
  "hf_space": {
20846
  "path": "hf_space:TASK_METHOD_20_RESULT_MATRIX.md",
20847
  "exists": true,
20848
+ "bytes": 4144,
20849
+ "sha256": "dac2828ba0286bc35290a61b6d02dbd75f0b3acb8d47a73cfa7f072d7fa209c1"
20850
  },
20851
  "hf_artifacts": {
20852
  "path": "hf_artifacts:TASK_METHOD_20_RESULT_MATRIX.md",
20853
  "exists": true,
20854
+ "bytes": 4144,
20855
+ "sha256": "dac2828ba0286bc35290a61b6d02dbd75f0b3acb8d47a73cfa7f072d7fa209c1"
20856
  },
20857
  "hf_model": {
20858
  "path": "hf_model:TASK_METHOD_20_RESULT_MATRIX.md",
20859
  "exists": true,
20860
+ "bytes": 4144,
20861
+ "sha256": "dac2828ba0286bc35290a61b6d02dbd75f0b3acb8d47a73cfa7f072d7fa209c1"
20862
  }
20863
  },
20864
  "failures": []
docs/data/publication_audit.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "status": "pass",
3
- "generated_at_utc": "2026-06-18T09:30:36+00:00",
4
  "checks": [
5
  {
6
  "name": "required_publication_assets_present",
@@ -164,6 +164,7 @@
164
  "scripts/publish_hf_bundles.py": true,
165
  "scripts/omni/build_128_episode_feature_index.py": true,
166
  "scripts/omni/build_task_suite_enhancement_128.py": true,
 
167
  "scripts/omni/train_qwen3_omni_lora.py": true,
168
  "results/omni_finetune/task_suite_enhancement_128_v1_20260608/enhancement_plan.json": true,
169
  "results/omni_finetune/task_suite_enhancement_128_v1_20260608/ENHANCEMENT_REPORT.md": true
@@ -214,8 +215,8 @@
214
  "github_repo": {
215
  "root": "repo",
216
  "exists": true,
217
- "file_count": 1263,
218
- "text_file_count": 1060,
219
  "largest_file": {
220
  "path": "results/episode_task_suite/modality_reconstruction/predictions.npz",
221
  "bytes": 55702978
 
1
  {
2
  "status": "pass",
3
+ "generated_at_utc": "2026-06-18T10:04:59+00:00",
4
  "checks": [
5
  {
6
  "name": "required_publication_assets_present",
 
164
  "scripts/publish_hf_bundles.py": true,
165
  "scripts/omni/build_128_episode_feature_index.py": true,
166
  "scripts/omni/build_task_suite_enhancement_128.py": true,
167
+ "scripts/omni/collect_qwen3_retrieval_task_probe_results.sh": true,
168
  "scripts/omni/train_qwen3_omni_lora.py": true,
169
  "results/omni_finetune/task_suite_enhancement_128_v1_20260608/enhancement_plan.json": true,
170
  "results/omni_finetune/task_suite_enhancement_128_v1_20260608/ENHANCEMENT_REPORT.md": true
 
215
  "github_repo": {
216
  "root": "repo",
217
  "exists": true,
218
+ "file_count": 1264,
219
+ "text_file_count": 1061,
220
  "largest_file": {
221
  "path": "results/episode_task_suite/modality_reconstruction/predictions.npz",
222
  "bytes": 55702978
docs/data/quality_gates.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "title": "Ropedia Xperience-10M Release Checks",
3
  "status": "pass",
4
- "generated_at_utc": "2026-06-18T09:31:04+00:00",
5
  "rule": "A release is current when the automated reports pass and the live GitHub/Hugging Face mirrors are verified after publishing.",
6
  "automated_gates": [
7
  {
 
1
  {
2
  "title": "Ropedia Xperience-10M Release Checks",
3
  "status": "pass",
4
+ "generated_at_utc": "2026-06-18T10:05:25+00:00",
5
  "rule": "A release is current when the automated reports pass and the live GitHub/Hugging Face mirrors are verified after publishing.",
6
  "automated_gates": [
7
  {
docs/data/scope_claims_audit.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "status": "pass",
3
- "generated_at_utc": "2026-06-18T09:28:46+00:00",
4
  "summary": {
5
  "qwen3_omni_verified_diagnostic_pilot": true,
6
  "dataset_manifest_num_episodes": 119,
 
1
  {
2
  "status": "pass",
3
+ "generated_at_utc": "2026-06-18T10:04:37+00:00",
4
  "summary": {
5
  "qwen3_omni_verified_diagnostic_pilot": true,
6
  "dataset_manifest_num_episodes": 119,
docs/data/single_episode_task_model_radar.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "title": "Single-Episode 20-Task Radar",
3
  "status": "pass",
4
- "generated_at_utc": "2026-06-18T09:06:25+00:00",
5
  "description": "Minimal and Neural MLP baselines on the one public sample episode, both scored on all 20 task contracts.",
6
  "task_count": 20,
7
  "method_count": 2,
 
1
  {
2
  "title": "Single-Episode 20-Task Radar",
3
  "status": "pass",
4
+ "generated_at_utc": "2026-06-18T10:04:17+00:00",
5
  "description": "Minimal and Neural MLP baselines on the one public sample episode, both scored on all 20 task contracts.",
6
  "task_count": 20,
7
  "method_count": 2,
docs/data/source_alignment_audit.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "title": "Ropedia Xperience-10M Source Alignment Note",
3
  "status": "pass",
4
- "generated_at_utc": "2026-06-18T09:28:24+00:00",
5
  "alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
6
  "alignment_summary": {
7
  "full_dataset_repo": "ropedia-ai/xperience-10m",
 
1
  {
2
  "title": "Ropedia Xperience-10M Source Alignment Note",
3
  "status": "pass",
4
+ "generated_at_utc": "2026-06-18T10:04:36+00:00",
5
  "alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
6
  "alignment_summary": {
7
  "full_dataset_repo": "ropedia-ai/xperience-10m",
docs/data/task_method_20_gap_audit.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "generated_at_utc": "2026-06-18T09:06:40+00:00",
3
  "immediate_actions": [
4
  {
5
  "artifact": "docs/data/task_method_20_gap_audit.json",
6
  "id": "gap_audit",
7
- "purpose": "Keep the 60 scoreless cells visible and reproducible."
8
  },
9
  {
10
  "artifact": "scripts/omni/score_model_output_probes.py",
@@ -101,11 +101,11 @@
101
  "proxy_scored_task_count": 0,
102
  "result_record_count": 20,
103
  "scope": "128 selected episodes, held-out test",
104
- "scored_task_count": 14,
105
- "scoreless_task_count": 6,
106
  "status_counts": {
107
- "not_evaluated_in_verified_package": 6,
108
- "scored": 14
109
  }
110
  },
111
  "raw128_neural_mlp": {
@@ -140,10 +140,10 @@
140
  "cosmos3_super_reasoner": 13,
141
  "metadata128_neural_mlp": 14,
142
  "metadata128_simple": 12,
143
- "qwen3_omni_v6_lora": 6
144
  },
145
  "missing_by_status": {
146
- "not_evaluated_in_verified_package": 34,
147
  "not_supported_by_metadata_only_package": 22,
148
  "unsupported_without_required_target": 4
149
  },
@@ -169,8 +169,7 @@
169
  "09 Cross-Modal Retrieval": [
170
  "cosmos3_super_reasoner",
171
  "metadata128_neural_mlp",
172
- "metadata128_simple",
173
- "qwen3_omni_v6_lora"
174
  ],
175
  "10 Cross-Modal Reconstruction": [
176
  "cosmos3_nano_future_window",
@@ -398,19 +397,6 @@
398
  "task_label": "Cross-Modal Retrieval",
399
  "task_number": 9
400
  },
401
- {
402
- "method": "Qwen3-Omni v6 LoRA",
403
- "metric_key": "mrr",
404
- "reason": "the verified public model package did not ask this branch to emit that task target; a new task-specific evaluation package is required for a numeric score",
405
- "recommended_next_step": "Generate verified model outputs for this task contract and score them against the held-out labels.",
406
- "scope": "multi_episode_128_partial_model_overlay",
407
- "series_id": "qwen3_omni_v6_lora",
408
- "status": "not_evaluated_in_verified_package",
409
- "status_label": "not evaluated",
410
- "task_id": "cross_modal_retrieval",
411
- "task_label": "Cross-Modal Retrieval",
412
- "task_number": 9
413
- },
414
  {
415
  "method": "Cosmos3-Super Reasoner",
416
  "metric_key": "mrr",
@@ -1069,8 +1055,8 @@
1069
  "method_count": 9,
1070
  "method_task_record_count": 180,
1071
  "proxy_scored_method_task_count": 4,
1072
- "scored_method_task_count": 120,
1073
- "scoreless_method_task_count": 60,
1074
  "task_count": 20
1075
  },
1076
  "source_matrix": "docs/data/task_method_20_result_matrix.json",
 
1
  {
2
+ "generated_at_utc": "2026-06-18T10:04:17+00:00",
3
  "immediate_actions": [
4
  {
5
  "artifact": "docs/data/task_method_20_gap_audit.json",
6
  "id": "gap_audit",
7
+ "purpose": "Keep the 59 scoreless cells visible and reproducible."
8
  },
9
  {
10
  "artifact": "scripts/omni/score_model_output_probes.py",
 
101
  "proxy_scored_task_count": 0,
102
  "result_record_count": 20,
103
  "scope": "128 selected episodes, held-out test",
104
+ "scored_task_count": 15,
105
+ "scoreless_task_count": 5,
106
  "status_counts": {
107
+ "not_evaluated_in_verified_package": 5,
108
+ "scored": 15
109
  }
110
  },
111
  "raw128_neural_mlp": {
 
140
  "cosmos3_super_reasoner": 13,
141
  "metadata128_neural_mlp": 14,
142
  "metadata128_simple": 12,
143
+ "qwen3_omni_v6_lora": 5
144
  },
145
  "missing_by_status": {
146
+ "not_evaluated_in_verified_package": 33,
147
  "not_supported_by_metadata_only_package": 22,
148
  "unsupported_without_required_target": 4
149
  },
 
169
  "09 Cross-Modal Retrieval": [
170
  "cosmos3_super_reasoner",
171
  "metadata128_neural_mlp",
172
+ "metadata128_simple"
 
173
  ],
174
  "10 Cross-Modal Reconstruction": [
175
  "cosmos3_nano_future_window",
 
397
  "task_label": "Cross-Modal Retrieval",
398
  "task_number": 9
399
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
400
  {
401
  "method": "Cosmos3-Super Reasoner",
402
  "metric_key": "mrr",
 
1055
  "method_count": 9,
1056
  "method_task_record_count": 180,
1057
  "proxy_scored_method_task_count": 4,
1058
+ "scored_method_task_count": 121,
1059
+ "scoreless_method_task_count": 59,
1060
  "task_count": 20
1061
  },
1062
  "source_matrix": "docs/data/task_method_20_result_matrix.json",
docs/data/task_method_20_result_matrix.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
  "title": "Task Method 20-Result Matrix",
3
  "status": "pass",
4
- "generated_at_utc": "2026-06-18T09:06:25+00:00",
5
  "task_count": 20,
6
  "method_count": 9,
7
  "method_task_record_count": 180,
8
- "scored_method_task_count": 120,
9
  "series": [
10
  {
11
  "id": "minimal",
@@ -161,17 +161,17 @@
161
  "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future-task probes scored from task-specific JSON.",
162
  "plotted_as": "colored point overlay",
163
  "result_record_count": 20,
164
- "scored_task_count": 14,
165
- "covered_task_count": 14,
166
  "proxy_scored_task_count": 0,
167
- "scoreless_task_count": 6,
168
  "unsupported_task_count": 0,
169
- "not_evaluated_task_count": 6,
170
  "status_counts": {
171
- "not_evaluated_in_verified_package": 6,
172
- "scored": 14
173
  },
174
- "coverage_fraction": 0.7,
175
  "result_record_fraction": 1.0
176
  },
177
  {
@@ -1634,17 +1634,17 @@
1634
  "task_label": "Cross-Modal Retrieval",
1635
  "series_id": "qwen3_omni_v6_lora",
1636
  "method": "Qwen3-Omni v6 LoRA",
1637
- "status": "not_evaluated_in_verified_package",
1638
- "status_label": "not evaluated",
1639
- "scored": false,
1640
  "proxy_scored": false,
1641
- "raw": null,
1642
- "raw_text": "n/a",
1643
- "normalized_score": null,
1644
- "metric_key": "mrr",
1645
- "source": null,
1646
  "scope": "multi_episode_128_partial_model_overlay",
1647
- "reason": "the verified public model package did not ask this branch to emit that task target; a new task-specific evaluation package is required for a numeric score"
1648
  },
1649
  {
1650
  "task_number": 9,
 
1
  {
2
  "title": "Task Method 20-Result Matrix",
3
  "status": "pass",
4
+ "generated_at_utc": "2026-06-18T10:04:17+00:00",
5
  "task_count": 20,
6
  "method_count": 9,
7
  "method_task_record_count": 180,
8
+ "scored_method_task_count": 121,
9
  "series": [
10
  {
11
  "id": "minimal",
 
161
  "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future-task probes scored from task-specific JSON.",
162
  "plotted_as": "colored point overlay",
163
  "result_record_count": 20,
164
+ "scored_task_count": 15,
165
+ "covered_task_count": 15,
166
  "proxy_scored_task_count": 0,
167
+ "scoreless_task_count": 5,
168
  "unsupported_task_count": 0,
169
+ "not_evaluated_task_count": 5,
170
  "status_counts": {
171
+ "not_evaluated_in_verified_package": 5,
172
+ "scored": 15
173
  },
174
+ "coverage_fraction": 0.75,
175
  "result_record_fraction": 1.0
176
  },
177
  {
 
1634
  "task_label": "Cross-Modal Retrieval",
1635
  "series_id": "qwen3_omni_v6_lora",
1636
  "method": "Qwen3-Omni v6 LoRA",
1637
+ "status": "scored",
1638
+ "status_label": "scored",
1639
+ "scored": true,
1640
  "proxy_scored": false,
1641
+ "raw": 0.5080191798941732,
1642
+ "raw_text": "0.5080",
1643
+ "normalized_score": 0.5080191798941732,
1644
+ "metric_key": "cross_modal_retrieval_mrr",
1645
+ "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json",
1646
  "scope": "multi_episode_128_partial_model_overlay",
1647
+ "reason": null
1648
  },
1649
  {
1650
  "task_number": 9,
docs/data/unified_task_model_radar.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
  "title": "Unified 20-Task Model Radar",
3
  "status": "pass",
4
- "generated_at_utc": "2026-06-18T09:06:25+00:00",
5
  "task_count": 20,
6
  "method_count": 9,
7
  "method_task_record_count": 180,
8
- "scored_method_task_count": 120,
9
  "normalization_policy": {
10
  "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
11
  "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -170,17 +170,17 @@
170
  "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future-task probes scored from task-specific JSON.",
171
  "plotted_as": "colored point overlay",
172
  "result_record_count": 20,
173
- "scored_task_count": 14,
174
- "covered_task_count": 14,
175
  "proxy_scored_task_count": 0,
176
- "scoreless_task_count": 6,
177
  "unsupported_task_count": 0,
178
- "not_evaluated_task_count": 6,
179
  "status_counts": {
180
- "not_evaluated_in_verified_package": 6,
181
- "scored": 14
182
  },
183
- "coverage_fraction": 0.7,
184
  "result_record_fraction": 1.0
185
  },
186
  {
@@ -1164,6 +1164,17 @@
1164
  "raw_text": "0.0221",
1165
  "status_label": "scored"
1166
  },
 
 
 
 
 
 
 
 
 
 
 
1167
  "metadata128_simple": {
1168
  "raw": null,
1169
  "metric_key": "mrr",
@@ -1208,17 +1219,6 @@
1208
  "raw_text": "n/a",
1209
  "status_label": "not supported"
1210
  },
1211
- "qwen3_omni_v6_lora": {
1212
- "raw": null,
1213
- "metric_key": "mrr",
1214
- "source": null,
1215
- "scope": "multi_episode_128_partial_model_overlay",
1216
- "status": "not_evaluated_in_verified_package",
1217
- "reason": "the verified public model package did not ask this branch to emit that task target; a new task-specific evaluation package is required for a numeric score",
1218
- "normalized_score": null,
1219
- "raw_text": "n/a",
1220
- "status_label": "not evaluated"
1221
- },
1222
  "cosmos3_super_reasoner": {
1223
  "raw": null,
1224
  "metric_key": "mrr",
@@ -2492,7 +2492,7 @@
2492
  "title": "Qwen3-Omni v6 LoRA",
2493
  "status": "verified",
2494
  "task_aligned_axes": "Qwen3",
2495
- "coverage": "20 records / 14 scored task-aligned axes",
2496
  "headline": "JSON validity 0.9990; action macro-F1 0.0029",
2497
  "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json"
2498
  },
@@ -3932,17 +3932,17 @@
3932
  "task_label": "Cross-Modal Retrieval",
3933
  "series_id": "qwen3_omni_v6_lora",
3934
  "method": "Qwen3-Omni v6 LoRA",
3935
- "status": "not_evaluated_in_verified_package",
3936
- "status_label": "not evaluated",
3937
- "scored": false,
3938
  "proxy_scored": false,
3939
- "raw": null,
3940
- "raw_text": "n/a",
3941
- "normalized_score": null,
3942
- "metric_key": "mrr",
3943
- "source": null,
3944
  "scope": "multi_episode_128_partial_model_overlay",
3945
- "reason": "the verified public model package did not ask this branch to emit that task target; a new task-specific evaluation package is required for a numeric score"
3946
  },
3947
  {
3948
  "task_number": 9,
 
1
  {
2
  "title": "Unified 20-Task Model Radar",
3
  "status": "pass",
4
+ "generated_at_utc": "2026-06-18T10:04:17+00:00",
5
  "task_count": 20,
6
  "method_count": 9,
7
  "method_task_record_count": 180,
8
+ "scored_method_task_count": 121,
9
  "normalization_policy": {
10
  "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
11
  "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
 
170
  "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future-task probes scored from task-specific JSON.",
171
  "plotted_as": "colored point overlay",
172
  "result_record_count": 20,
173
+ "scored_task_count": 15,
174
+ "covered_task_count": 15,
175
  "proxy_scored_task_count": 0,
176
+ "scoreless_task_count": 5,
177
  "unsupported_task_count": 0,
178
+ "not_evaluated_task_count": 5,
179
  "status_counts": {
180
+ "not_evaluated_in_verified_package": 5,
181
+ "scored": 15
182
  },
183
+ "coverage_fraction": 0.75,
184
  "result_record_fraction": 1.0
185
  },
186
  {
 
1164
  "raw_text": "0.0221",
1165
  "status_label": "scored"
1166
  },
1167
+ "qwen3_omni_v6_lora": {
1168
+ "raw": 0.5080191798941732,
1169
+ "metric_key": "cross_modal_retrieval_mrr",
1170
+ "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json",
1171
+ "scope": "multi_episode_128_partial_model_overlay",
1172
+ "status": "scored",
1173
+ "reason": null,
1174
+ "normalized_score": 0.5080191798941732,
1175
+ "raw_text": "0.5080",
1176
+ "status_label": "scored"
1177
+ },
1178
  "metadata128_simple": {
1179
  "raw": null,
1180
  "metric_key": "mrr",
 
1219
  "raw_text": "n/a",
1220
  "status_label": "not supported"
1221
  },
 
 
 
 
 
 
 
 
 
 
 
1222
  "cosmos3_super_reasoner": {
1223
  "raw": null,
1224
  "metric_key": "mrr",
 
2492
  "title": "Qwen3-Omni v6 LoRA",
2493
  "status": "verified",
2494
  "task_aligned_axes": "Qwen3",
2495
+ "coverage": "20 records / 15 scored task-aligned axes",
2496
  "headline": "JSON validity 0.9990; action macro-F1 0.0029",
2497
  "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json"
2498
  },
 
3932
  "task_label": "Cross-Modal Retrieval",
3933
  "series_id": "qwen3_omni_v6_lora",
3934
  "method": "Qwen3-Omni v6 LoRA",
3935
+ "status": "scored",
3936
+ "status_label": "scored",
3937
+ "scored": true,
3938
  "proxy_scored": false,
3939
+ "raw": 0.5080191798941732,
3940
+ "raw_text": "0.5080",
3941
+ "normalized_score": 0.5080191798941732,
3942
+ "metric_key": "cross_modal_retrieval_mrr",
3943
+ "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json",
3944
  "scope": "multi_episode_128_partial_model_overlay",
3945
+ "reason": null
3946
  },
3947
  {
3948
  "task_number": 9,
results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/RUN_REPORT.md ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ # Qwen3-Omni v6 Retrieval Task Probes
2
+
3
+ - Run ID: `xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z`
4
+ - Shards: `2`
5
+
6
+ | Task | Metric | Score | Samples |
7
+ | --- | --- | ---: | ---: |
8
+ | Cross-Modal Retrieval | cross_modal_retrieval_mrr | 0.508019 | 4032 |
results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/collection_validation.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "records": [
3
+ {
4
+ "metric_key": "cross_modal_retrieval_mrr",
5
+ "num_samples": 4032,
6
+ "primary_score": 0.5080191798941732,
7
+ "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json",
8
+ "task_id": "cross_modal_retrieval"
9
+ }
10
+ ],
11
+ "run_id": "xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z",
12
+ "status": "pass",
13
+ "summary": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/summary.json",
14
+ "title": "Qwen3 Retrieval Task Probe Collection Validation",
15
+ "validated_task_count": 1
16
+ }
results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_dir": "/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite/checkpoints/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora/adapter_lora",
3
+ "candidate_count": 4,
4
+ "caption_grounding_mrr": 0.5080191798941732,
5
+ "cross_modal_retrieval_mrr": 0.5080191798941732,
6
+ "dataset_jsonl": "/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite/results/omni_finetune/xperience10m_qwen3_omni_128ep_multiscale_cap96_v5_full8gpu_lora_dataset/dataset_a100_eval.jsonl",
7
+ "eval_split": "test",
8
+ "metric_key": "cross_modal_retrieval_mrr",
9
+ "model_id": "/mnt/kgc/chaoyue/ropedia-h20-side/modelscope_models/Qwen__Qwen3-Omni-30B-A3B-Instruct",
10
+ "mrr": 0.5080191798941732,
11
+ "num_samples": 4032,
12
+ "primary_metric": "cross_modal_retrieval_mrr",
13
+ "primary_score": 0.5080191798941732,
14
+ "run_id": "xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z",
15
+ "sample_offset": 0,
16
+ "sample_stride": 1,
17
+ "scope": "held_out_test_qwen3_retrieval_task_probe",
18
+ "score_policy": "GPU-backed Qwen3-Omni v6 sensor-to-video retrieval probe. The query is a compact summary of held-out motion-capture, body-contact, camera-pose, and IMU feature blocks; candidates are shuffled staged mosaic video windows, and the score is MRR of the synchronized true window. No action/subtask/object labels are included in the query.",
19
+ "status": "pass",
20
+ "task_id": "cross_modal_retrieval",
21
+ "task_label": "Cross-Modal Retrieval",
22
+ "task_number": 9,
23
+ "title": "Qwen3-Omni v6 Cross-Modal Retrieval",
24
+ "top1_accuracy": 0.24032738095238096
25
+ }
results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/launch_env.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ run_id=xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z
2
+ dataset_jsonl=/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite/results/omni_finetune/xperience10m_qwen3_omni_128ep_multiscale_cap96_v5_full8gpu_lora_dataset/dataset_a100_eval.jsonl
3
+ model_dir=/mnt/kgc/chaoyue/ropedia-h20-side/modelscope_models/Qwen__Qwen3-Omni-30B-A3B-Instruct
4
+ adapter_dir=/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite/checkpoints/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora/adapter_lora
5
+ tasks=cross_modal_retrieval
6
+ candidate_count=4
7
+ cuda_device_groups=0,1 2,3
8
+ shards=2
9
+ started_at=2026-06-18T14:33:01+08:00
10
+ finished_at=2026-06-18T18:01:20+08:00
11
+ exit_code=0
results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/summary.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "run_id": "xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z",
3
+ "shard_dirs": [
4
+ "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z_shard0",
5
+ "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z_shard1"
6
+ ],
7
+ "status": "pass",
8
+ "tasks": {
9
+ "cross_modal_retrieval": {
10
+ "metric_key": "cross_modal_retrieval_mrr",
11
+ "metrics_json": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json",
12
+ "num_samples": 4032,
13
+ "primary_score": 0.5080191798941732,
14
+ "task_label": "Cross-Modal Retrieval",
15
+ "task_number": 9
16
+ }
17
+ },
18
+ "title": "Qwen3-Omni v6 Retrieval Task Probes"
19
+ }
results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z_shard0.progress.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z_shard1.progress.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/RUN_REPORT.md ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ # Qwen3-Omni v6 Retrieval Task Probes
2
+
3
+ - Run ID: `xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z`
4
+ - Shards: `2`
5
+
6
+ | Task | Metric | Score | Samples |
7
+ | --- | --- | ---: | ---: |
8
+ | Language Grounding | caption_grounding_mrr | 0.876447 | 4032 |
results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/caption_grounding/metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_dir": "/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite/checkpoints/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora/adapter_lora",
3
+ "candidate_count": 4,
4
+ "caption_grounding_mrr": 0.8764467592592605,
5
+ "dataset_jsonl": "/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite/results/omni_finetune/xperience10m_qwen3_omni_128ep_multiscale_cap96_v5_full8gpu_lora_dataset/dataset_a100_eval.jsonl",
6
+ "eval_split": "test",
7
+ "metric_key": "caption_grounding_mrr",
8
+ "model_id": "/mnt/kgc/chaoyue/ropedia-h20-side/modelscope_models/Qwen__Qwen3-Omni-30B-A3B-Instruct",
9
+ "mrr": 0.8764467592592605,
10
+ "num_samples": 4032,
11
+ "primary_metric": "caption_grounding_mrr",
12
+ "primary_score": 0.8764467592592605,
13
+ "run_id": "xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z",
14
+ "sample_offset": 0,
15
+ "sample_stride": 1,
16
+ "scope": "held_out_test_qwen3_retrieval_task_probe",
17
+ "score_policy": "GPU-backed Qwen3-Omni v6 text-to-video retrieval probe. The text query is built from held-out action/subtask/object labels, candidates are shuffled staged mosaic video windows, and the score is MRR of the true window. This does not score tasks whose numeric/raw targets are absent from the export.",
18
+ "status": "pass",
19
+ "task_id": "caption_grounding",
20
+ "task_label": "Language Grounding",
21
+ "task_number": 8,
22
+ "title": "Qwen3-Omni v6 Language Grounding",
23
+ "top1_accuracy": 0.7864583333333334
24
+ }
results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/caption_grounding/predictions.csv ADDED
The diff for this file is too large to render. See raw diff
 
results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/collection_validation.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "records": [
3
+ {
4
+ "metric_key": "caption_grounding_mrr",
5
+ "num_samples": 4032,
6
+ "primary_score": 0.8764467592592605,
7
+ "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/caption_grounding/metrics.json",
8
+ "task_id": "caption_grounding"
9
+ }
10
+ ],
11
+ "run_id": "xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z",
12
+ "status": "pass",
13
+ "summary": "results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/summary.json",
14
+ "title": "Qwen3 Future Task Probe Collection Validation",
15
+ "validated_task_count": 1
16
+ }
results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/launch_env.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ run_id=xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z
2
+ dataset_jsonl=/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite/results/omni_finetune/xperience10m_qwen3_omni_128ep_multiscale_cap96_v5_full8gpu_lora_dataset/dataset_a100_eval.jsonl
3
+ model_dir=/mnt/kgc/chaoyue/ropedia-h20-side/modelscope_models/Qwen__Qwen3-Omni-30B-A3B-Instruct
4
+ adapter_dir=/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite/checkpoints/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora/adapter_lora
5
+ tasks=caption_grounding
6
+ candidate_count=4
7
+ cuda_device_groups=0,1 2,3
8
+ shards=2
9
+ started_at=2026-06-18T05:20:16+08:00
10
+ finished_at=2026-06-18T08:41:05+08:00
11
+ exit_code=0
results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/summary.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "run_id": "xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z",
3
+ "shard_dirs": [
4
+ "results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z_shard0",
5
+ "results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z_shard1"
6
+ ],
7
+ "status": "pass",
8
+ "tasks": {
9
+ "caption_grounding": {
10
+ "metric_key": "caption_grounding_mrr",
11
+ "metrics_json": "results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/caption_grounding/metrics.json",
12
+ "num_samples": 4032,
13
+ "primary_score": 0.8764467592592605,
14
+ "task_label": "Language Grounding",
15
+ "task_number": 8
16
+ }
17
+ },
18
+ "title": "Qwen3-Omni v6 Retrieval Task Probes"
19
+ }
results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z_shard0.progress.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z_shard1.progress.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
scripts/omni/collect_qwen3_retrieval_task_probe_results.sh ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ set -euo pipefail
3
+
4
+ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
5
+ PROJECT_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
6
+
7
+ GPU_HOST_SUFFIX="${GPU_HOST_SUFFIX:-$(printf 'A%s-80Gx4' 100)}"
8
+ REMOTE_HOST="${REMOTE_HOST:-ANGEL-${GPU_HOST_SUFFIX}}"
9
+ REMOTE_ROOT="${REMOTE_ROOT:-/mnt/kgc/chaoyue/ropedia-h20-side/ropedia-episode-task-suite}"
10
+ RUN_ID="${RUN_ID:-xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z}"
11
+ RESULT_ROOT="${RESULT_ROOT:-results/omni_finetune}"
12
+ TASKS_CSV="${TASKS_CSV:-cross_modal_retrieval}"
13
+
14
+ REMOTE_RUN_DIR="${REMOTE_ROOT}/${RESULT_ROOT}/${RUN_ID}"
15
+ LOCAL_RUN_DIR="${PROJECT_ROOT}/${RESULT_ROOT}/${RUN_ID}"
16
+ LOCAL_LAUNCHER_DIR="${PROJECT_ROOT}/${RESULT_ROOT}/deferred_launchers"
17
+ REMOTE_LAUNCHER_LOG="${REMOTE_ROOT}/${RESULT_ROOT}/${RUN_ID}.launch.log"
18
+
19
+ IFS=',' read -r -a TASKS <<< "$TASKS_CSV"
20
+
21
+ echo "checking remote run ${REMOTE_HOST}:${REMOTE_RUN_DIR}"
22
+ ssh "$REMOTE_HOST" "cd '$REMOTE_ROOT' && test -s '${RESULT_ROOT}/${RUN_ID}/summary.json'"
23
+ for task_id in "${TASKS[@]}"; do
24
+ ssh "$REMOTE_HOST" "cd '$REMOTE_ROOT' && test -s '${RESULT_ROOT}/${RUN_ID}/${task_id}/metrics.json'"
25
+ done
26
+
27
+ mkdir -p "$LOCAL_RUN_DIR" "$LOCAL_LAUNCHER_DIR"
28
+ rsync -av "${REMOTE_HOST}:${REMOTE_RUN_DIR}/" "$LOCAL_RUN_DIR/"
29
+ ssh "$REMOTE_HOST" "test -s '$REMOTE_LAUNCHER_LOG'" >/dev/null 2>&1 \
30
+ && rsync -av "${REMOTE_HOST}:${REMOTE_LAUNCHER_LOG}" "$LOCAL_LAUNCHER_DIR/" \
31
+ || true
32
+
33
+ python3 - "$PROJECT_ROOT" "$RUN_ID" "$TASKS_CSV" <<'PY'
34
+ import json
35
+ import sys
36
+ from pathlib import Path
37
+
38
+ root = Path(sys.argv[1])
39
+ run_id = sys.argv[2]
40
+ task_ids = [item.strip() for item in sys.argv[3].split(",") if item.strip()]
41
+ run_dir = root / "results/omni_finetune" / run_id
42
+ metric_key_by_task = {
43
+ "caption_grounding": "caption_grounding_mrr",
44
+ "cross_modal_retrieval": "cross_modal_retrieval_mrr",
45
+ }
46
+ expected = {task_id: metric_key_by_task[task_id] for task_id in task_ids}
47
+
48
+ summary_path = run_dir / "summary.json"
49
+ if not summary_path.exists():
50
+ raise SystemExit(f"missing summary: {summary_path}")
51
+ summary = json.loads(summary_path.read_text(encoding="utf-8"))
52
+ if summary.get("status") != "pass":
53
+ raise SystemExit(f"run summary is not pass: {summary.get('status')}")
54
+
55
+ records = []
56
+ for task_id, metric_key in expected.items():
57
+ metrics_path = run_dir / task_id / "metrics.json"
58
+ if not metrics_path.exists():
59
+ raise SystemExit(f"missing metrics: {metrics_path}")
60
+ metrics = json.loads(metrics_path.read_text(encoding="utf-8"))
61
+ score = metrics.get(metric_key)
62
+ if metrics.get("status") != "pass" or not isinstance(score, (int, float)):
63
+ raise SystemExit(f"invalid {task_id} metric {metric_key}: {score!r}")
64
+ records.append(
65
+ {
66
+ "task_id": task_id,
67
+ "metric_key": metric_key,
68
+ "primary_score": score,
69
+ "num_samples": metrics.get("num_samples"),
70
+ "source": str(metrics_path.relative_to(root)),
71
+ }
72
+ )
73
+
74
+ validation = {
75
+ "title": "Qwen3 Retrieval Task Probe Collection Validation",
76
+ "status": "pass",
77
+ "run_id": run_id,
78
+ "summary": str(summary_path.relative_to(root)),
79
+ "validated_task_count": len(records),
80
+ "records": records,
81
+ }
82
+ (run_dir / "collection_validation.json").write_text(
83
+ json.dumps(validation, indent=2, sort_keys=True) + "\n",
84
+ encoding="utf-8",
85
+ )
86
+ print(json.dumps(validation, indent=2, sort_keys=True))
87
+ PY
88
+
89
+ echo "collected and validated ${LOCAL_RUN_DIR}"