Add files using upload-large-folder tool

docs/data/artifact_index.json

@@ -1,13 +1,13 @@
 {
   "title": "Ropedia Xperience-10M Task Suite Artifact Index",
-  "generated_at_utc": "2026-06-16T12:01:29+00:00",
+  "generated_at_utc": "2026-06-16T13:35:38+00:00",
   "status": "pass",
-  "artifact_count": 189,
+  "artifact_count": 191,
   "missing": [],
   "by_kind": {
     "project_path": 14,
     "scaleup_contract": 7,
-    "scaleup_status": 41,
+    "scaleup_status": 42,
     "publication_workflow": 6,
     "reproducibility": 4,
     "project_scope": 1,
@@ -16,7 +16,7 @@
     "website_data": 10,
     "generated_figure": 7,
     "visualization_builder": 1,
-    "model_result": 2,
+    "model_result": 3,
     "result_interpretation": 5,
     "metrics_source": 27,
     "visual_evidence": 7,
@@ -465,7 +465,7 @@
       "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
       "exists": true,
       "bytes": 4432,
-      "sha256": "fce9e1525d5bfb4ddbdd0d36febfcf7df9f7115e29457f85ff322db1e7418a1d"
+      "sha256": "4c6e5505884c13ad9d60195e977d1554adafe2a83d07307644532d77f36850bb"
     },
     {
       "id": "source_alignment_validator",
@@ -585,8 +585,8 @@
       "surface": "website_hf",
       "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3/Cosmos overlay mappings, branch-card caveats, and explicit scoreless status records.",
       "exists": true,
-      "bytes": 231290,
-      "sha256": "851677db9ca0a3255d44e5540c2fbd19b3bb4ae5a0d8e31b8faa62f9d6c73a60"
+      "bytes": 231251,
+      "sha256": "5cbcdf8e3a659ef98bbc623ee3e434055ad6479599c95178587b3dab84a6072d"
     },
     {
       "id": "single_episode_task_model_radar_json",
@@ -597,7 +597,7 @@
       "shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
       "exists": true,
       "bytes": 50973,
-      "sha256": "08904cd9b7a7f2d7090dd232ef026b21a9aaf1891ebff250ab768dce09e71749"
+      "sha256": "10f9ca6afc9f9d69d2380faab2e2f1ebd0114bf7ab778ea30188ba849e9a44c1"
     },
     {
       "id": "episode128_task_model_radar_json",
@@ -607,8 +607,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines and verified Qwen3/Cosmos branches, preserving explicit scoreless cells.",
       "exists": true,
-      "bytes": 187439,
-      "sha256": "98b3e4367bcdbb22f21bb03896f1ee6db305bafca7b26e4ffd7a3418aa12d95e"
+      "bytes": 187400,
+      "sha256": "fab3dc021cfeca3547b72fd2e1321a1258c0c48a8eaa5ea5cc28600badcd2c68"
     },
     {
       "id": "task_method_20_result_matrix_json",
@@ -618,8 +618,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and scoreless cells carry unsupported/not-evaluated reasons.",
       "exists": true,
-      "bytes": 129711,
-      "sha256": "b15009dd8c4caf77d62654f1dcc80e3fe328dcebd80e397e679f1a44597f3294"
+      "bytes": 129740,
+      "sha256": "e7e398b98e4e188ee883a126bd77ad966ba563f2c43da56e13e871b6dc90f1ea"
     },
     {
       "id": "task_method_20_result_matrix",
@@ -629,8 +629,8 @@
       "surface": "repo_hf",
       "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.",
       "exists": true,
-      "bytes": 4224,
-      "sha256": "fe14a0e1709a8bb5b9fb1fd720ffde0aecfed578329d8e1e71b352a83b23b1f8"
+      "bytes": 4208,
+      "sha256": "bfe01b258fe121448d2b5b188c6995041c81d7ce1286dcd2ee0bf9c01d6a6193"
     },
     {
       "id": "task_method_20_gap_audit_json",
@@ -638,10 +638,10 @@
       "path": "docs/data/task_method_20_gap_audit.json",
       "kind": "website_data",
       "surface": "website_hf",
-      "shows": "Machine-readable 180-record gap ledger with 111 numeric scores, 69 scoreless cells, explicit status reasons, and next evidence needed before new scores can be published.",
+      "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.",
       "exists": true,
-      "bytes": 59421,
-      "sha256": "872954cbf001c2286b186e17c8d590d9d637852cade0ecc2357c63247e4803fb"
+      "bytes": 57943,
+      "sha256": "a1246c07c569238e8589fab0fb90e86733b7799816e8ef6690036a0fac289ecb"
     },
     {
       "id": "task_method_20_gap_audit",
@@ -651,8 +651,8 @@
       "surface": "repo_hf",
       "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.",
       "exists": true,
-      "bytes": 16600,
-      "sha256": "e6bd5b49d01eb095fe6f0d38436e08f2c2ff1a4449f98a08928d51e965e563bb"
+      "bytes": 16234,
+      "sha256": "351e55637374770221115486fd6ef46550ae923c4fae5c01d3bb1e777b5a44fb"
     },
     {
       "id": "unified_task_model_radar_chart",
@@ -662,8 +662,8 @@
       "surface": "website_hf",
       "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3/Cosmos task-aligned model overlays.",
       "exists": true,
-      "bytes": 49046,
-      "sha256": "60c4ed6818b1ebf00165fc7187613c8e41bc0359d5053dfc3659f497f4acef44"
+      "bytes": 49695,
+      "sha256": "2ad63af1cd1e3e6f9c354b20792c20683e8877e2f92d9da5b5284dce56e668b7"
     },
     {
       "id": "single_episode_task_model_radar_chart",
@@ -684,8 +684,8 @@
       "surface": "website_hf",
       "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.",
       "exists": true,
-      "bytes": 43020,
-      "sha256": "fad2d354e09ece917350dbbb66a65a4dcfabc38e000da61b002315c67b6aefa9"
+      "bytes": 43679,
+      "sha256": "51991fd33719be32da422f559b7d27895fc96b1332b0952f0c19b573d58c1325"
     },
     {
       "id": "unified_task_model_radar_builder",
@@ -695,8 +695,8 @@
       "surface": "repo_hf",
       "shows": "Regenerates the direction-aware radar chart and machine-readable metric overlay JSON.",
       "exists": true,
-      "bytes": 47539,
-      "sha256": "23a655bc2ba72e5326a0db8a5cad06d297d5fb76d7985135192f1d34368b966b"
+      "bytes": 48861,
+      "sha256": "621ff19f057e6ed279388c8e944f2e4a2cfc87b9be1bd9f1feee6d329f0ec431"
     },
     {
       "id": "task_method_20_gap_audit_builder",
@@ -706,8 +706,8 @@
       "surface": "repo_hf",
       "shows": "Regenerates the public gap audit from the 9-method by 20-task matrix without inventing scores for unsupported or unevaluated cells.",
       "exists": true,
-      "bytes": 9959,
-      "sha256": "6a0086ccbc567529b2b24061ca36228e8eac213331621bc66b96db2aea62e1f4"
+      "bytes": 10094,
+      "sha256": "4ba5a43fa045b02303ba16a146ab15a891155370a85dd7c09cbe68f8f0eac7ed"
     },
     {
       "id": "all_task_model_scoring_waiter",
@@ -742,6 +742,28 @@
       "bytes": 9133,
       "sha256": "3a867d0333fe591999715158e311011db25da018ca39c9b4638930841f35efb8"
     },
+    {
+      "id": "existing_model_output_task_probe",
+      "title": "Existing model-output task probe package",
+      "path": "results/omni_finetune/model_output_task_probes_20260616/summary.json",
+      "kind": "model_result",
+      "surface": "repo_hf",
+      "shows": "Scores task 16 action-object relation only where verified held-out prediction JSON already contains action and object-set fields.",
+      "exists": true,
+      "bytes": 2000,
+      "sha256": "de95421d93fec5d12049e492db9fbe7c10af5c2cd0d1039da82c05ec82bf98c5"
+    },
+    {
+      "id": "existing_model_output_task_probe_script",
+      "title": "Existing model-output task probe scorer",
+      "path": "scripts/omni/score_existing_model_output_task_probes.py",
+      "kind": "scaleup_status",
+      "surface": "repo_hf",
+      "shows": "Derives task-specific scores from committed verified model outputs without running new inference or backfilling absent targets.",
+      "exists": true,
+      "bytes": 13291,
+      "sha256": "25b8e7ba394c1e604fe8d7c900a013b3ea330f32b393cdcd416b2d0f3a2727b8"
+    },
     {
       "id": "a100_128_metadata_task_baselines",
       "title": "128-episode metadata task baselines",
@@ -949,7 +971,7 @@
       "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
       "exists": true,
       "bytes": 8100,
-      "sha256": "9d6069e48f2ee57b910193ff3c5f52233c3864a85e3c4e753ecf6f2b411c54ac"
+      "sha256": "b9f9236ae07336c8984a65bcda558d49453c2e57f6c903a44235bec4fd0d8df0"
     },
     {
       "id": "public_surface_qa",
@@ -971,7 +993,7 @@
       "volatile": true,
       "shows": "Machine-readable report for SEO/social metadata, accessible tab semantics, public links, project links, and clear project presentation.",
       "exists": true,
-      "bytes": 6096,
+      "bytes": 6146,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1096,8 +1118,8 @@
       "surface": "repo_hf",
       "shows": "Generates the selective artifact catalog from local files.",
       "exists": true,
-      "bytes": 53849,
-      "sha256": "c6407d4644cd6fee2981a6240c8087b0a83e43133aeb5bcff52d67b27f469e2d"
+      "bytes": 54683,
+      "sha256": "0a9e7c7391f0e2822d8490ddd216f155e1ce3a50d2ba3c90476ee09685f74d65"
     },
     {
       "id": "publication_audit",
@@ -1108,7 +1130,7 @@
       "volatile": true,
       "shows": "Confirms public bundles exclude raw data, caches, heavy archives, and credential text.",
       "exists": true,
-      "bytes": 8189,
+      "bytes": 8298,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1132,7 +1154,7 @@
       "volatile": true,
       "shows": "Confirms prepared GitHub/HF Space/artifact/model mirrors share the same critical data, figure, website HTML, and validator files.",
       "exists": true,
-      "bytes": 847909,
+      "bytes": 868302,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1144,7 +1166,7 @@
       "volatile": true,
       "shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
       "exists": true,
-      "bytes": 18814,
+      "bytes": 18933,
       "hash_policy": "existence_and_size_only"
     },
     {

docs/data/episode128_task_model_radar.json

@@ -1,12 +1,12 @@
 {
   "title": "128-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-16T11:26:57+00:00",
+  "generated_at_utc": "2026-06-16T13:35:38+00:00",
   "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.",
   "task_count": 20,
   "method_count": 7,
   "method_task_record_count": 140,
-  "scored_method_task_count": 71,
+  "scored_method_task_count": 73,
   "normalization_policy": {
     "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
     "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -124,20 +124,20 @@
       "kind": "partial_128_episode_foundation_model_overlay",
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
-      "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics on task-aligned JSON outputs.",
+      "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 scored from existing verified action/object JSON.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 6,
-      "covered_task_count": 6,
+      "scored_task_count": 7,
+      "covered_task_count": 7,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 14,
+      "scoreless_task_count": 13,
       "unsupported_task_count": 0,
-      "not_evaluated_task_count": 14,
+      "not_evaluated_task_count": 13,
       "status_counts": {
-        "not_evaluated_in_verified_package": 14,
-        "scored": 6
+        "not_evaluated_in_verified_package": 13,
+        "scored": 7
       },
-      "coverage_fraction": 0.3,
+      "coverage_fraction": 0.35,
       "result_record_fraction": 1.0
     },
     {
@@ -148,20 +148,20 @@
       "kind": "partial_128_episode_foundation_model_overlay",
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
-      "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation.",
+      "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 16 scored from existing verified action/object JSON.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 6,
-      "covered_task_count": 6,
+      "scored_task_count": 7,
+      "covered_task_count": 7,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 14,
+      "scoreless_task_count": 13,
       "unsupported_task_count": 0,
-      "not_evaluated_task_count": 14,
+      "not_evaluated_task_count": 13,
       "status_counts": {
-        "not_evaluated_in_verified_package": 14,
-        "scored": 6
+        "not_evaluated_in_verified_package": 13,
+        "scored": 7
       },
-      "coverage_fraction": 0.3,
+      "coverage_fraction": 0.35,
       "result_record_fraction": 1.0
     },
     {
@@ -1612,26 +1612,26 @@
           "status_label": "scored"
         },
         "qwen3_omni_v6_lora": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
+          "raw": 0.0002220083079671497,
+          "metric_key": "action_object_relation_macro_f1",
+          "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
           "scope": "multi_episode_128_partial_model_overlay",
-          "status": "not_evaluated_in_verified_package",
-          "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",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not evaluated"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0002220083079671497,
+          "raw_text": "0.0002",
+          "status_label": "scored"
         },
         "cosmos3_super_reasoner": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
+          "raw": 0.0,
+          "metric_key": "action_object_relation_macro_f1",
+          "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
           "scope": "multi_episode_128_partial_model_overlay",
-          "status": "not_evaluated_in_verified_package",
-          "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",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not evaluated"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "cosmos3_nano_future_window": {
           "raw": null,
@@ -3980,17 +3980,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "qwen3_omni_v6_lora",
       "method": "Qwen3-Omni v6 LoRA",
-      "status": "not_evaluated_in_verified_package",
-      "status_label": "not evaluated",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
-      "metric_key": "macro_f1",
-      "source": null,
+      "raw": 0.0002220083079671497,
+      "raw_text": "0.0002",
+      "normalized_score": 0.0002220083079671497,
+      "metric_key": "action_object_relation_macro_f1",
+      "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
       "scope": "multi_episode_128_partial_model_overlay",
-      "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"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -3998,17 +3998,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "cosmos3_super_reasoner",
       "method": "Cosmos3-Super Reasoner",
-      "status": "not_evaluated_in_verified_package",
-      "status_label": "not evaluated",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
-      "metric_key": "macro_f1",
-      "source": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
+      "metric_key": "action_object_relation_macro_f1",
+      "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
       "scope": "multi_episode_128_partial_model_overlay",
-      "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"
+      "reason": null
     },
     {
       "task_number": 16,

docs/data/mirror_parity.json

@@ -1,9 +1,9 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-16T12:05:03+00:00",
+  "generated_at_utc": "2026-06-16T13:35:58+00:00",
   "hf_root": "hf_publish",
   "summary": {
-    "group_count": 578,
+    "group_count": 587,
     "failure_count": 0,
     "failures_by_surface": {}
   },
@@ -138,45 +138,45 @@
       "local": {
         "path": "repo:docs/data/artifact_index.json",
         "exists": true,
-        "bytes": 103135,
-        "sha256": "7477a20154930bf56c85d8973cafa2636e68fc0fc20b2fac47ba39cd0b96bb52"
+        "bytes": 104199,
+        "sha256": "785793bcd8ec76149d03ca6fe7f9539ce1bb0fbdf62091fc57de87c123bc49c6"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/artifact_index.json",
           "exists": true,
-          "bytes": 103135,
-          "sha256": "7477a20154930bf56c85d8973cafa2636e68fc0fc20b2fac47ba39cd0b96bb52"
+          "bytes": 104199,
+          "sha256": "785793bcd8ec76149d03ca6fe7f9539ce1bb0fbdf62091fc57de87c123bc49c6"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/artifact_index.json",
           "exists": true,
-          "bytes": 103135,
-          "sha256": "7477a20154930bf56c85d8973cafa2636e68fc0fc20b2fac47ba39cd0b96bb52"
+          "bytes": 104199,
+          "sha256": "785793bcd8ec76149d03ca6fe7f9539ce1bb0fbdf62091fc57de87c123bc49c6"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 103135,
-          "sha256": "7477a20154930bf56c85d8973cafa2636e68fc0fc20b2fac47ba39cd0b96bb52"
+          "bytes": 104199,
+          "sha256": "785793bcd8ec76149d03ca6fe7f9539ce1bb0fbdf62091fc57de87c123bc49c6"
         },
         "hf_model_data": {
           "path": "hf_model:data/artifact_index.json",
           "exists": true,
-          "bytes": 103135,
-          "sha256": "7477a20154930bf56c85d8973cafa2636e68fc0fc20b2fac47ba39cd0b96bb52"
+          "bytes": 104199,
+          "sha256": "785793bcd8ec76149d03ca6fe7f9539ce1bb0fbdf62091fc57de87c123bc49c6"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 103135,
-          "sha256": "7477a20154930bf56c85d8973cafa2636e68fc0fc20b2fac47ba39cd0b96bb52"
+          "bytes": 104199,
+          "sha256": "785793bcd8ec76149d03ca6fe7f9539ce1bb0fbdf62091fc57de87c123bc49c6"
         },
         "hf_model": {
           "path": "hf_model:metrics/artifact_index.json",
           "exists": true,
-          "bytes": 103135,
-          "sha256": "7477a20154930bf56c85d8973cafa2636e68fc0fc20b2fac47ba39cd0b96bb52"
+          "bytes": 104199,
+          "sha256": "785793bcd8ec76149d03ca6fe7f9539ce1bb0fbdf62091fc57de87c123bc49c6"
         }
       },
       "failures": []
@@ -825,44 +825,44 @@
         "path": "repo:docs/data/publication_audit.json",
         "exists": true,
         "bytes": 8298,
-        "sha256": "c202aea91c9a6e311c190255b51217b6e91cfee45ae8db2cb7ee5174e9ceed28"
+        "sha256": "c102f6b278caca6f359330f130cd3299b09ad219ba6fcedf14416542d8f935a6"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/publication_audit.json",
           "exists": true,
           "bytes": 8298,
-          "sha256": "c202aea91c9a6e311c190255b51217b6e91cfee45ae8db2cb7ee5174e9ceed28"
+          "sha256": "c102f6b278caca6f359330f130cd3299b09ad219ba6fcedf14416542d8f935a6"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/publication_audit.json",
           "exists": true,
           "bytes": 8298,
-          "sha256": "c202aea91c9a6e311c190255b51217b6e91cfee45ae8db2cb7ee5174e9ceed28"
+          "sha256": "c102f6b278caca6f359330f130cd3299b09ad219ba6fcedf14416542d8f935a6"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 8298,
-          "sha256": "c202aea91c9a6e311c190255b51217b6e91cfee45ae8db2cb7ee5174e9ceed28"
+          "sha256": "c102f6b278caca6f359330f130cd3299b09ad219ba6fcedf14416542d8f935a6"
         },
         "hf_model_data": {
           "path": "hf_model:data/publication_audit.json",
           "exists": true,
           "bytes": 8298,
-          "sha256": "c202aea91c9a6e311c190255b51217b6e91cfee45ae8db2cb7ee5174e9ceed28"
+          "sha256": "c102f6b278caca6f359330f130cd3299b09ad219ba6fcedf14416542d8f935a6"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 8298,
-          "sha256": "c202aea91c9a6e311c190255b51217b6e91cfee45ae8db2cb7ee5174e9ceed28"
+          "sha256": "c102f6b278caca6f359330f130cd3299b09ad219ba6fcedf14416542d8f935a6"
         },
         "hf_model": {
           "path": "hf_model:metrics/publication_audit.json",
           "exists": true,
           "bytes": 8298,
-          "sha256": "c202aea91c9a6e311c190255b51217b6e91cfee45ae8db2cb7ee5174e9ceed28"
+          "sha256": "c102f6b278caca6f359330f130cd3299b09ad219ba6fcedf14416542d8f935a6"
         }
       },
       "failures": []
@@ -874,44 +874,44 @@
         "path": "repo:docs/data/public_surface_qa.json",
         "exists": true,
         "bytes": 6146,
-        "sha256": "087dd5d2cd87fdc86cd16df74b6f8db23180c84af829e153ccadf646f7c998be"
+        "sha256": "e8de5e0cd4d4042b056bd37963c1da98b01589cf4aaf68c8954f9eed2688683d"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/public_surface_qa.json",
           "exists": true,
           "bytes": 6146,
-          "sha256": "087dd5d2cd87fdc86cd16df74b6f8db23180c84af829e153ccadf646f7c998be"
+          "sha256": "e8de5e0cd4d4042b056bd37963c1da98b01589cf4aaf68c8954f9eed2688683d"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/public_surface_qa.json",
           "exists": true,
           "bytes": 6146,
-          "sha256": "087dd5d2cd87fdc86cd16df74b6f8db23180c84af829e153ccadf646f7c998be"
+          "sha256": "e8de5e0cd4d4042b056bd37963c1da98b01589cf4aaf68c8954f9eed2688683d"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 6146,
-          "sha256": "087dd5d2cd87fdc86cd16df74b6f8db23180c84af829e153ccadf646f7c998be"
+          "sha256": "e8de5e0cd4d4042b056bd37963c1da98b01589cf4aaf68c8954f9eed2688683d"
         },
         "hf_model_data": {
           "path": "hf_model:data/public_surface_qa.json",
           "exists": true,
           "bytes": 6146,
-          "sha256": "087dd5d2cd87fdc86cd16df74b6f8db23180c84af829e153ccadf646f7c998be"
+          "sha256": "e8de5e0cd4d4042b056bd37963c1da98b01589cf4aaf68c8954f9eed2688683d"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 6146,
-          "sha256": "087dd5d2cd87fdc86cd16df74b6f8db23180c84af829e153ccadf646f7c998be"
+          "sha256": "e8de5e0cd4d4042b056bd37963c1da98b01589cf4aaf68c8954f9eed2688683d"
         },
         "hf_model": {
           "path": "hf_model:metrics/public_surface_qa.json",
           "exists": true,
           "bytes": 6146,
-          "sha256": "087dd5d2cd87fdc86cd16df74b6f8db23180c84af829e153ccadf646f7c998be"
+          "sha256": "e8de5e0cd4d4042b056bd37963c1da98b01589cf4aaf68c8954f9eed2688683d"
         }
       },
       "failures": []
@@ -1021,44 +1021,44 @@
         "path": "repo:docs/data/quality_gates.json",
         "exists": true,
         "bytes": 8100,
-        "sha256": "6b952e2866cd38e7f190f24530ab78d1625b8cb94d0cd8b675b594fda3df235b"
+        "sha256": "69babe425b30b76780fddac26f88c81dc9ea034b5c39e85dccd58d7e58deef44"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/quality_gates.json",
           "exists": true,
           "bytes": 8100,
-          "sha256": "6b952e2866cd38e7f190f24530ab78d1625b8cb94d0cd8b675b594fda3df235b"
+          "sha256": "69babe425b30b76780fddac26f88c81dc9ea034b5c39e85dccd58d7e58deef44"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/quality_gates.json",
           "exists": true,
           "bytes": 8100,
-          "sha256": "6b952e2866cd38e7f190f24530ab78d1625b8cb94d0cd8b675b594fda3df235b"
+          "sha256": "69babe425b30b76780fddac26f88c81dc9ea034b5c39e85dccd58d7e58deef44"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8100,
-          "sha256": "6b952e2866cd38e7f190f24530ab78d1625b8cb94d0cd8b675b594fda3df235b"
+          "sha256": "69babe425b30b76780fddac26f88c81dc9ea034b5c39e85dccd58d7e58deef44"
         },
         "hf_model_data": {
           "path": "hf_model:data/quality_gates.json",
           "exists": true,
           "bytes": 8100,
-          "sha256": "6b952e2866cd38e7f190f24530ab78d1625b8cb94d0cd8b675b594fda3df235b"
+          "sha256": "69babe425b30b76780fddac26f88c81dc9ea034b5c39e85dccd58d7e58deef44"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8100,
-          "sha256": "6b952e2866cd38e7f190f24530ab78d1625b8cb94d0cd8b675b594fda3df235b"
+          "sha256": "69babe425b30b76780fddac26f88c81dc9ea034b5c39e85dccd58d7e58deef44"
         },
         "hf_model": {
           "path": "hf_model:metrics/quality_gates.json",
           "exists": true,
           "bytes": 8100,
-          "sha256": "6b952e2866cd38e7f190f24530ab78d1625b8cb94d0cd8b675b594fda3df235b"
+          "sha256": "69babe425b30b76780fddac26f88c81dc9ea034b5c39e85dccd58d7e58deef44"
         }
       },
       "failures": []
@@ -1462,44 +1462,44 @@
         "path": "repo:docs/data/scope_claims_audit.json",
         "exists": true,
         "bytes": 21630,
-        "sha256": "403dd79220a3322ff575074a6a4073de74f2c4688c566ba479785d7495872dc3"
+        "sha256": "d0653f4dc77b25127dad6d9615da0e89e4259de20daed61effaccfed8aa4438f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21630,
-          "sha256": "403dd79220a3322ff575074a6a4073de74f2c4688c566ba479785d7495872dc3"
+          "sha256": "d0653f4dc77b25127dad6d9615da0e89e4259de20daed61effaccfed8aa4438f"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21630,
-          "sha256": "403dd79220a3322ff575074a6a4073de74f2c4688c566ba479785d7495872dc3"
+          "sha256": "d0653f4dc77b25127dad6d9615da0e89e4259de20daed61effaccfed8aa4438f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21630,
-          "sha256": "403dd79220a3322ff575074a6a4073de74f2c4688c566ba479785d7495872dc3"
+          "sha256": "d0653f4dc77b25127dad6d9615da0e89e4259de20daed61effaccfed8aa4438f"
         },
         "hf_model_data": {
           "path": "hf_model:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21630,
-          "sha256": "403dd79220a3322ff575074a6a4073de74f2c4688c566ba479785d7495872dc3"
+          "sha256": "d0653f4dc77b25127dad6d9615da0e89e4259de20daed61effaccfed8aa4438f"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21630,
-          "sha256": "403dd79220a3322ff575074a6a4073de74f2c4688c566ba479785d7495872dc3"
+          "sha256": "d0653f4dc77b25127dad6d9615da0e89e4259de20daed61effaccfed8aa4438f"
         },
         "hf_model": {
           "path": "hf_model:metrics/scope_claims_audit.json",
           "exists": true,
           "bytes": 21630,
-          "sha256": "403dd79220a3322ff575074a6a4073de74f2c4688c566ba479785d7495872dc3"
+          "sha256": "d0653f4dc77b25127dad6d9615da0e89e4259de20daed61effaccfed8aa4438f"
         }
       },
       "failures": []
@@ -1560,44 +1560,44 @@
         "path": "repo:docs/data/source_alignment_audit.json",
         "exists": true,
         "bytes": 4432,
-        "sha256": "7abfe3e11f8c92399b96b0fe3d5edc1ee501666553ca162ba9958e5684ba1940"
+        "sha256": "3e2021bb443cb8f8f844aa1491e8874ea6f3d7c500c40a616213e6812236ffd6"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "7abfe3e11f8c92399b96b0fe3d5edc1ee501666553ca162ba9958e5684ba1940"
+          "sha256": "3e2021bb443cb8f8f844aa1491e8874ea6f3d7c500c40a616213e6812236ffd6"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "7abfe3e11f8c92399b96b0fe3d5edc1ee501666553ca162ba9958e5684ba1940"
+          "sha256": "3e2021bb443cb8f8f844aa1491e8874ea6f3d7c500c40a616213e6812236ffd6"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "7abfe3e11f8c92399b96b0fe3d5edc1ee501666553ca162ba9958e5684ba1940"
+          "sha256": "3e2021bb443cb8f8f844aa1491e8874ea6f3d7c500c40a616213e6812236ffd6"
         },
         "hf_model_data": {
           "path": "hf_model:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "7abfe3e11f8c92399b96b0fe3d5edc1ee501666553ca162ba9958e5684ba1940"
+          "sha256": "3e2021bb443cb8f8f844aa1491e8874ea6f3d7c500c40a616213e6812236ffd6"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "7abfe3e11f8c92399b96b0fe3d5edc1ee501666553ca162ba9958e5684ba1940"
+          "sha256": "3e2021bb443cb8f8f844aa1491e8874ea6f3d7c500c40a616213e6812236ffd6"
         },
         "hf_model": {
           "path": "hf_model:metrics/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "7abfe3e11f8c92399b96b0fe3d5edc1ee501666553ca162ba9958e5684ba1940"
+          "sha256": "3e2021bb443cb8f8f844aa1491e8874ea6f3d7c500c40a616213e6812236ffd6"
         }
       },
       "failures": []
@@ -1658,44 +1658,44 @@
         "path": "repo:docs/data/single_episode_task_model_radar.json",
         "exists": true,
         "bytes": 50973,
-        "sha256": "08904cd9b7a7f2d7090dd232ef026b21a9aaf1891ebff250ab768dce09e71749"
+        "sha256": "10f9ca6afc9f9d69d2380faab2e2f1ebd0114bf7ab778ea30188ba849e9a44c1"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/single_episode_task_model_radar.json",
           "exists": true,
           "bytes": 50973,
-          "sha256": "08904cd9b7a7f2d7090dd232ef026b21a9aaf1891ebff250ab768dce09e71749"
+          "sha256": "10f9ca6afc9f9d69d2380faab2e2f1ebd0114bf7ab778ea30188ba849e9a44c1"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/single_episode_task_model_radar.json",
           "exists": true,
           "bytes": 50973,
-          "sha256": "08904cd9b7a7f2d7090dd232ef026b21a9aaf1891ebff250ab768dce09e71749"
+          "sha256": "10f9ca6afc9f9d69d2380faab2e2f1ebd0114bf7ab778ea30188ba849e9a44c1"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/single_episode_task_model_radar.json",
           "exists": true,
           "bytes": 50973,
-          "sha256": "08904cd9b7a7f2d7090dd232ef026b21a9aaf1891ebff250ab768dce09e71749"
+          "sha256": "10f9ca6afc9f9d69d2380faab2e2f1ebd0114bf7ab778ea30188ba849e9a44c1"
         },
         "hf_model_data": {
           "path": "hf_model:data/single_episode_task_model_radar.json",
           "exists": true,
           "bytes": 50973,
-          "sha256": "08904cd9b7a7f2d7090dd232ef026b21a9aaf1891ebff250ab768dce09e71749"
+          "sha256": "10f9ca6afc9f9d69d2380faab2e2f1ebd0114bf7ab778ea30188ba849e9a44c1"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/single_episode_task_model_radar.json",
           "exists": true,
           "bytes": 50973,
-          "sha256": "08904cd9b7a7f2d7090dd232ef026b21a9aaf1891ebff250ab768dce09e71749"
+          "sha256": "10f9ca6afc9f9d69d2380faab2e2f1ebd0114bf7ab778ea30188ba849e9a44c1"
         },
         "hf_model": {
           "path": "hf_model:metrics/single_episode_task_model_radar.json",
           "exists": true,
           "bytes": 50973,
-          "sha256": "08904cd9b7a7f2d7090dd232ef026b21a9aaf1891ebff250ab768dce09e71749"
+          "sha256": "10f9ca6afc9f9d69d2380faab2e2f1ebd0114bf7ab778ea30188ba849e9a44c1"
         }
       },
       "failures": []
@@ -1706,45 +1706,45 @@
       "local": {
         "path": "repo:docs/data/episode128_task_model_radar.json",
         "exists": true,
-        "bytes": 187439,
-        "sha256": "98b3e4367bcdbb22f21bb03896f1ee6db305bafca7b26e4ffd7a3418aa12d95e"
+        "bytes": 187400,
+        "sha256": "fab3dc021cfeca3547b72fd2e1321a1258c0c48a8eaa5ea5cc28600badcd2c68"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 187439,
-          "sha256": "98b3e4367bcdbb22f21bb03896f1ee6db305bafca7b26e4ffd7a3418aa12d95e"
+          "bytes": 187400,
+          "sha256": "fab3dc021cfeca3547b72fd2e1321a1258c0c48a8eaa5ea5cc28600badcd2c68"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 187439,
-          "sha256": "98b3e4367bcdbb22f21bb03896f1ee6db305bafca7b26e4ffd7a3418aa12d95e"
+          "bytes": 187400,
+          "sha256": "fab3dc021cfeca3547b72fd2e1321a1258c0c48a8eaa5ea5cc28600badcd2c68"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 187439,
-          "sha256": "98b3e4367bcdbb22f21bb03896f1ee6db305bafca7b26e4ffd7a3418aa12d95e"
+          "bytes": 187400,
+          "sha256": "fab3dc021cfeca3547b72fd2e1321a1258c0c48a8eaa5ea5cc28600badcd2c68"
         },
         "hf_model_data": {
           "path": "hf_model:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 187439,
-          "sha256": "98b3e4367bcdbb22f21bb03896f1ee6db305bafca7b26e4ffd7a3418aa12d95e"
+          "bytes": 187400,
+          "sha256": "fab3dc021cfeca3547b72fd2e1321a1258c0c48a8eaa5ea5cc28600badcd2c68"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 187439,
-          "sha256": "98b3e4367bcdbb22f21bb03896f1ee6db305bafca7b26e4ffd7a3418aa12d95e"
+          "bytes": 187400,
+          "sha256": "fab3dc021cfeca3547b72fd2e1321a1258c0c48a8eaa5ea5cc28600badcd2c68"
         },
         "hf_model": {
           "path": "hf_model:metrics/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 187439,
-          "sha256": "98b3e4367bcdbb22f21bb03896f1ee6db305bafca7b26e4ffd7a3418aa12d95e"
+          "bytes": 187400,
+          "sha256": "fab3dc021cfeca3547b72fd2e1321a1258c0c48a8eaa5ea5cc28600badcd2c68"
         }
       },
       "failures": []
@@ -1854,44 +1854,44 @@
         "path": "repo:docs/data/task_surface_integrity.json",
         "exists": true,
         "bytes": 45779,
-        "sha256": "aca78406b797e12bfcb5d0dfb19c720ab153ff80943b501894a31c2f5f850b41"
+        "sha256": "5cc466a245de221f9980e0a2f42df016c096515f1074d08bf2be8e758a876612"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "aca78406b797e12bfcb5d0dfb19c720ab153ff80943b501894a31c2f5f850b41"
+          "sha256": "5cc466a245de221f9980e0a2f42df016c096515f1074d08bf2be8e758a876612"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "aca78406b797e12bfcb5d0dfb19c720ab153ff80943b501894a31c2f5f850b41"
+          "sha256": "5cc466a245de221f9980e0a2f42df016c096515f1074d08bf2be8e758a876612"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "aca78406b797e12bfcb5d0dfb19c720ab153ff80943b501894a31c2f5f850b41"
+          "sha256": "5cc466a245de221f9980e0a2f42df016c096515f1074d08bf2be8e758a876612"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "aca78406b797e12bfcb5d0dfb19c720ab153ff80943b501894a31c2f5f850b41"
+          "sha256": "5cc466a245de221f9980e0a2f42df016c096515f1074d08bf2be8e758a876612"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "aca78406b797e12bfcb5d0dfb19c720ab153ff80943b501894a31c2f5f850b41"
+          "sha256": "5cc466a245de221f9980e0a2f42df016c096515f1074d08bf2be8e758a876612"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "aca78406b797e12bfcb5d0dfb19c720ab153ff80943b501894a31c2f5f850b41"
+          "sha256": "5cc466a245de221f9980e0a2f42df016c096515f1074d08bf2be8e758a876612"
         }
       },
       "failures": []
@@ -1951,45 +1951,45 @@
       "local": {
         "path": "repo:docs/data/task_method_20_result_matrix.json",
         "exists": true,
-        "bytes": 129711,
-        "sha256": "b15009dd8c4caf77d62654f1dcc80e3fe328dcebd80e397e679f1a44597f3294"
+        "bytes": 129740,
+        "sha256": "e7e398b98e4e188ee883a126bd77ad966ba563f2c43da56e13e871b6dc90f1ea"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 129711,
-          "sha256": "b15009dd8c4caf77d62654f1dcc80e3fe328dcebd80e397e679f1a44597f3294"
+          "bytes": 129740,
+          "sha256": "e7e398b98e4e188ee883a126bd77ad966ba563f2c43da56e13e871b6dc90f1ea"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 129711,
-          "sha256": "b15009dd8c4caf77d62654f1dcc80e3fe328dcebd80e397e679f1a44597f3294"
+          "bytes": 129740,
+          "sha256": "e7e398b98e4e188ee883a126bd77ad966ba563f2c43da56e13e871b6dc90f1ea"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 129711,
-          "sha256": "b15009dd8c4caf77d62654f1dcc80e3fe328dcebd80e397e679f1a44597f3294"
+          "bytes": 129740,
+          "sha256": "e7e398b98e4e188ee883a126bd77ad966ba563f2c43da56e13e871b6dc90f1ea"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 129711,
-          "sha256": "b15009dd8c4caf77d62654f1dcc80e3fe328dcebd80e397e679f1a44597f3294"
+          "bytes": 129740,
+          "sha256": "e7e398b98e4e188ee883a126bd77ad966ba563f2c43da56e13e871b6dc90f1ea"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 129711,
-          "sha256": "b15009dd8c4caf77d62654f1dcc80e3fe328dcebd80e397e679f1a44597f3294"
+          "bytes": 129740,
+          "sha256": "e7e398b98e4e188ee883a126bd77ad966ba563f2c43da56e13e871b6dc90f1ea"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 129711,
-          "sha256": "b15009dd8c4caf77d62654f1dcc80e3fe328dcebd80e397e679f1a44597f3294"
+          "bytes": 129740,
+          "sha256": "e7e398b98e4e188ee883a126bd77ad966ba563f2c43da56e13e871b6dc90f1ea"
         }
       },
       "failures": []
@@ -2000,45 +2000,45 @@
       "local": {
         "path": "repo:docs/data/task_method_20_gap_audit.json",
         "exists": true,
-        "bytes": 59421,
-        "sha256": "872954cbf001c2286b186e17c8d590d9d637852cade0ecc2357c63247e4803fb"
+        "bytes": 57943,
+        "sha256": "a1246c07c569238e8589fab0fb90e86733b7799816e8ef6690036a0fac289ecb"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_method_20_gap_audit.json",
           "exists": true,
-          "bytes": 59421,
-          "sha256": "872954cbf001c2286b186e17c8d590d9d637852cade0ecc2357c63247e4803fb"
+          "bytes": 57943,
+          "sha256": "a1246c07c569238e8589fab0fb90e86733b7799816e8ef6690036a0fac289ecb"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_method_20_gap_audit.json",
           "exists": true,
-          "bytes": 59421,
-          "sha256": "872954cbf001c2286b186e17c8d590d9d637852cade0ecc2357c63247e4803fb"
+          "bytes": 57943,
+          "sha256": "a1246c07c569238e8589fab0fb90e86733b7799816e8ef6690036a0fac289ecb"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_method_20_gap_audit.json",
           "exists": true,
-          "bytes": 59421,
-          "sha256": "872954cbf001c2286b186e17c8d590d9d637852cade0ecc2357c63247e4803fb"
+          "bytes": 57943,
+          "sha256": "a1246c07c569238e8589fab0fb90e86733b7799816e8ef6690036a0fac289ecb"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_method_20_gap_audit.json",
           "exists": true,
-          "bytes": 59421,
-          "sha256": "872954cbf001c2286b186e17c8d590d9d637852cade0ecc2357c63247e4803fb"
+          "bytes": 57943,
+          "sha256": "a1246c07c569238e8589fab0fb90e86733b7799816e8ef6690036a0fac289ecb"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_method_20_gap_audit.json",
           "exists": true,
-          "bytes": 59421,
-          "sha256": "872954cbf001c2286b186e17c8d590d9d637852cade0ecc2357c63247e4803fb"
+          "bytes": 57943,
+          "sha256": "a1246c07c569238e8589fab0fb90e86733b7799816e8ef6690036a0fac289ecb"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_method_20_gap_audit.json",
           "exists": true,
-          "bytes": 59421,
-          "sha256": "872954cbf001c2286b186e17c8d590d9d637852cade0ecc2357c63247e4803fb"
+          "bytes": 57943,
+          "sha256": "a1246c07c569238e8589fab0fb90e86733b7799816e8ef6690036a0fac289ecb"
         }
       },
       "failures": []
@@ -2098,45 +2098,45 @@
       "local": {
         "path": "repo:docs/data/unified_task_model_radar.json",
         "exists": true,
-        "bytes": 231290,
-        "sha256": "851677db9ca0a3255d44e5540c2fbd19b3bb4ae5a0d8e31b8faa62f9d6c73a60"
+        "bytes": 231251,
+        "sha256": "5cbcdf8e3a659ef98bbc623ee3e434055ad6479599c95178587b3dab84a6072d"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 231290,
-          "sha256": "851677db9ca0a3255d44e5540c2fbd19b3bb4ae5a0d8e31b8faa62f9d6c73a60"
+          "bytes": 231251,
+          "sha256": "5cbcdf8e3a659ef98bbc623ee3e434055ad6479599c95178587b3dab84a6072d"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 231290,
-          "sha256": "851677db9ca0a3255d44e5540c2fbd19b3bb4ae5a0d8e31b8faa62f9d6c73a60"
+          "bytes": 231251,
+          "sha256": "5cbcdf8e3a659ef98bbc623ee3e434055ad6479599c95178587b3dab84a6072d"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 231290,
-          "sha256": "851677db9ca0a3255d44e5540c2fbd19b3bb4ae5a0d8e31b8faa62f9d6c73a60"
+          "bytes": 231251,
+          "sha256": "5cbcdf8e3a659ef98bbc623ee3e434055ad6479599c95178587b3dab84a6072d"
         },
         "hf_model_data": {
           "path": "hf_model:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 231290,
-          "sha256": "851677db9ca0a3255d44e5540c2fbd19b3bb4ae5a0d8e31b8faa62f9d6c73a60"
+          "bytes": 231251,
+          "sha256": "5cbcdf8e3a659ef98bbc623ee3e434055ad6479599c95178587b3dab84a6072d"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 231290,
-          "sha256": "851677db9ca0a3255d44e5540c2fbd19b3bb4ae5a0d8e31b8faa62f9d6c73a60"
+          "bytes": 231251,
+          "sha256": "5cbcdf8e3a659ef98bbc623ee3e434055ad6479599c95178587b3dab84a6072d"
         },
         "hf_model": {
           "path": "hf_model:metrics/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 231290,
-          "sha256": "851677db9ca0a3255d44e5540c2fbd19b3bb4ae5a0d8e31b8faa62f9d6c73a60"
+          "bytes": 231251,
+          "sha256": "5cbcdf8e3a659ef98bbc623ee3e434055ad6479599c95178587b3dab84a6072d"
         }
       },
       "failures": []
@@ -2148,44 +2148,44 @@
         "path": "repo:docs/data/website_integrity.json",
         "exists": true,
         "bytes": 18933,
-        "sha256": "797890b784ff4da6566e31fa89887919ca3f01eb37d713678eb1d720fa9b8780"
+        "sha256": "9ad46ada8b1cae970c165bee1db3771e23d8e76cba84f72fd2c8d205715bc12a"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/website_integrity.json",
           "exists": true,
           "bytes": 18933,
-          "sha256": "797890b784ff4da6566e31fa89887919ca3f01eb37d713678eb1d720fa9b8780"
+          "sha256": "9ad46ada8b1cae970c165bee1db3771e23d8e76cba84f72fd2c8d205715bc12a"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/website_integrity.json",
           "exists": true,
           "bytes": 18933,
-          "sha256": "797890b784ff4da6566e31fa89887919ca3f01eb37d713678eb1d720fa9b8780"
+          "sha256": "9ad46ada8b1cae970c165bee1db3771e23d8e76cba84f72fd2c8d205715bc12a"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/website_integrity.json",
           "exists": true,
           "bytes": 18933,
-          "sha256": "797890b784ff4da6566e31fa89887919ca3f01eb37d713678eb1d720fa9b8780"
+          "sha256": "9ad46ada8b1cae970c165bee1db3771e23d8e76cba84f72fd2c8d205715bc12a"
         },
         "hf_model_data": {
           "path": "hf_model:data/website_integrity.json",
           "exists": true,
           "bytes": 18933,
-          "sha256": "797890b784ff4da6566e31fa89887919ca3f01eb37d713678eb1d720fa9b8780"
+          "sha256": "9ad46ada8b1cae970c165bee1db3771e23d8e76cba84f72fd2c8d205715bc12a"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/website_integrity.json",
           "exists": true,
           "bytes": 18933,
-          "sha256": "797890b784ff4da6566e31fa89887919ca3f01eb37d713678eb1d720fa9b8780"
+          "sha256": "9ad46ada8b1cae970c165bee1db3771e23d8e76cba84f72fd2c8d205715bc12a"
         },
         "hf_model": {
           "path": "hf_model:metrics/website_integrity.json",
           "exists": true,
           "bytes": 18933,
-          "sha256": "797890b784ff4da6566e31fa89887919ca3f01eb37d713678eb1d720fa9b8780"
+          "sha256": "9ad46ada8b1cae970c165bee1db3771e23d8e76cba84f72fd2c8d205715bc12a"
         }
       },
       "failures": []
@@ -2319,33 +2319,33 @@
       "local": {
         "path": "repo:docs/assets/charts/episode128_task_model_radar.svg",
         "exists": true,
-        "bytes": 43020,
-        "sha256": "fad2d354e09ece917350dbbb66a65a4dcfabc38e000da61b002315c67b6aefa9"
+        "bytes": 43679,
+        "sha256": "51991fd33719be32da422f559b7d27895fc96b1332b0952f0c19b573d58c1325"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 43020,
-          "sha256": "fad2d354e09ece917350dbbb66a65a4dcfabc38e000da61b002315c67b6aefa9"
+          "bytes": 43679,
+          "sha256": "51991fd33719be32da422f559b7d27895fc96b1332b0952f0c19b573d58c1325"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 43020,
-          "sha256": "fad2d354e09ece917350dbbb66a65a4dcfabc38e000da61b002315c67b6aefa9"
+          "bytes": 43679,
+          "sha256": "51991fd33719be32da422f559b7d27895fc96b1332b0952f0c19b573d58c1325"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 43020,
-          "sha256": "fad2d354e09ece917350dbbb66a65a4dcfabc38e000da61b002315c67b6aefa9"
+          "bytes": 43679,
+          "sha256": "51991fd33719be32da422f559b7d27895fc96b1332b0952f0c19b573d58c1325"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 43020,
-          "sha256": "fad2d354e09ece917350dbbb66a65a4dcfabc38e000da61b002315c67b6aefa9"
+          "bytes": 43679,
+          "sha256": "51991fd33719be32da422f559b7d27895fc96b1332b0952f0c19b573d58c1325"
         }
       },
       "failures": []
@@ -2393,33 +2393,33 @@
       "local": {
         "path": "repo:docs/assets/charts/unified_task_model_radar.svg",
         "exists": true,
-        "bytes": 49046,
-        "sha256": "60c4ed6818b1ebf00165fc7187613c8e41bc0359d5053dfc3659f497f4acef44"
+        "bytes": 49695,
+        "sha256": "2ad63af1cd1e3e6f9c354b20792c20683e8877e2f92d9da5b5284dce56e668b7"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 49046,
-          "sha256": "60c4ed6818b1ebf00165fc7187613c8e41bc0359d5053dfc3659f497f4acef44"
+          "bytes": 49695,
+          "sha256": "2ad63af1cd1e3e6f9c354b20792c20683e8877e2f92d9da5b5284dce56e668b7"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 49046,
-          "sha256": "60c4ed6818b1ebf00165fc7187613c8e41bc0359d5053dfc3659f497f4acef44"
+          "bytes": 49695,
+          "sha256": "2ad63af1cd1e3e6f9c354b20792c20683e8877e2f92d9da5b5284dce56e668b7"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 49046,
-          "sha256": "60c4ed6818b1ebf00165fc7187613c8e41bc0359d5053dfc3659f497f4acef44"
+          "bytes": 49695,
+          "sha256": "2ad63af1cd1e3e6f9c354b20792c20683e8877e2f92d9da5b5284dce56e668b7"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 49046,
-          "sha256": "60c4ed6818b1ebf00165fc7187613c8e41bc0359d5053dfc3659f497f4acef44"
+          "bytes": 49695,
+          "sha256": "2ad63af1cd1e3e6f9c354b20792c20683e8877e2f92d9da5b5284dce56e668b7"
         }
       },
       "failures": []
@@ -3650,6 +3650,31 @@
       },
       "failures": []
     },
+    {
+      "name": "scripts/omni/score_existing_model_output_task_probes.py",
+      "status": "pass",
+      "local": {
+        "path": "repo:scripts/omni/score_existing_model_output_task_probes.py",
+        "exists": true,
+        "bytes": 13291,
+        "sha256": "25b8e7ba394c1e604fe8d7c900a013b3ea330f32b393cdcd416b2d0f3a2727b8"
+      },
+      "mirrors": {
+        "hf_artifacts": {
+          "path": "hf_artifacts:scripts/omni/score_existing_model_output_task_probes.py",
+          "exists": true,
+          "bytes": 13291,
+          "sha256": "25b8e7ba394c1e604fe8d7c900a013b3ea330f32b393cdcd416b2d0f3a2727b8"
+        },
+        "hf_model": {
+          "path": "hf_model:scripts/omni/score_existing_model_output_task_probes.py",
+          "exists": true,
+          "bytes": 13291,
+          "sha256": "25b8e7ba394c1e604fe8d7c900a013b3ea330f32b393cdcd416b2d0f3a2727b8"
+        }
+      },
+      "failures": []
+    },
     {
       "name": "scripts/omni/score_model_output_probes.py",
       "status": "pass",
@@ -3806,21 +3831,21 @@
       "local": {
         "path": "repo:scripts/build_artifact_index.py",
         "exists": true,
-        "bytes": 53849,
-        "sha256": "c6407d4644cd6fee2981a6240c8087b0a83e43133aeb5bcff52d67b27f469e2d"
+        "bytes": 54683,
+        "sha256": "0a9e7c7391f0e2822d8490ddd216f155e1ce3a50d2ba3c90476ee09685f74d65"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 53849,
-          "sha256": "c6407d4644cd6fee2981a6240c8087b0a83e43133aeb5bcff52d67b27f469e2d"
+          "bytes": 54683,
+          "sha256": "0a9e7c7391f0e2822d8490ddd216f155e1ce3a50d2ba3c90476ee09685f74d65"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 53849,
-          "sha256": "c6407d4644cd6fee2981a6240c8087b0a83e43133aeb5bcff52d67b27f469e2d"
+          "bytes": 54683,
+          "sha256": "0a9e7c7391f0e2822d8490ddd216f155e1ce3a50d2ba3c90476ee09685f74d65"
         }
       },
       "failures": []
@@ -4031,21 +4056,21 @@
       "local": {
         "path": "repo:scripts/build_task_method_20_gap_audit.py",
         "exists": true,
-        "bytes": 9959,
-        "sha256": "6a0086ccbc567529b2b24061ca36228e8eac213331621bc66b96db2aea62e1f4"
+        "bytes": 10094,
+        "sha256": "4ba5a43fa045b02303ba16a146ab15a891155370a85dd7c09cbe68f8f0eac7ed"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_task_method_20_gap_audit.py",
           "exists": true,
-          "bytes": 9959,
-          "sha256": "6a0086ccbc567529b2b24061ca36228e8eac213331621bc66b96db2aea62e1f4"
+          "bytes": 10094,
+          "sha256": "4ba5a43fa045b02303ba16a146ab15a891155370a85dd7c09cbe68f8f0eac7ed"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_task_method_20_gap_audit.py",
           "exists": true,
-          "bytes": 9959,
-          "sha256": "6a0086ccbc567529b2b24061ca36228e8eac213331621bc66b96db2aea62e1f4"
+          "bytes": 10094,
+          "sha256": "4ba5a43fa045b02303ba16a146ab15a891155370a85dd7c09cbe68f8f0eac7ed"
         }
       },
       "failures": []
@@ -4106,21 +4131,21 @@
       "local": {
         "path": "repo:scripts/build_unified_task_model_radar.py",
         "exists": true,
-        "bytes": 47539,
-        "sha256": "23a655bc2ba72e5326a0db8a5cad06d297d5fb76d7985135192f1d34368b966b"
+        "bytes": 48861,
+        "sha256": "621ff19f057e6ed279388c8e944f2e4a2cfc87b9be1bd9f1feee6d329f0ec431"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_unified_task_model_radar.py",
           "exists": true,
-          "bytes": 47539,
-          "sha256": "23a655bc2ba72e5326a0db8a5cad06d297d5fb76d7985135192f1d34368b966b"
+          "bytes": 48861,
+          "sha256": "621ff19f057e6ed279388c8e944f2e4a2cfc87b9be1bd9f1feee6d329f0ec431"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_unified_task_model_radar.py",
           "exists": true,
-          "bytes": 47539,
-          "sha256": "23a655bc2ba72e5326a0db8a5cad06d297d5fb76d7985135192f1d34368b966b"
+          "bytes": 48861,
+          "sha256": "621ff19f057e6ed279388c8e944f2e4a2cfc87b9be1bd9f1feee6d329f0ec431"
         }
       },
       "failures": []
@@ -4181,21 +4206,21 @@
       "local": {
         "path": "repo:scripts/validate_mirror_parity.py",
         "exists": true,
-        "bytes": 24235,
-        "sha256": "c823c3c0fbcbc004aa890738c510183e06290687b42a8d42adccb385525b605a"
+        "bytes": 24812,
+        "sha256": "c7d67a9e371f20c24951fbc357f64907365e60acab5ff189fa1675ff631bd27f"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/validate_mirror_parity.py",
           "exists": true,
-          "bytes": 24235,
-          "sha256": "c823c3c0fbcbc004aa890738c510183e06290687b42a8d42adccb385525b605a"
+          "bytes": 24812,
+          "sha256": "c7d67a9e371f20c24951fbc357f64907365e60acab5ff189fa1675ff631bd27f"
         },
         "hf_model": {
           "path": "hf_model:scripts/validate_mirror_parity.py",
           "exists": true,
-          "bytes": 24235,
-          "sha256": "c823c3c0fbcbc004aa890738c510183e06290687b42a8d42adccb385525b605a"
+          "bytes": 24812,
+          "sha256": "c7d67a9e371f20c24951fbc357f64907365e60acab5ff189fa1675ff631bd27f"
         }
       },
       "failures": []
@@ -4331,21 +4356,21 @@
       "local": {
         "path": "repo:scripts/sync_hf_publish_mirrors.py",
         "exists": true,
-        "bytes": 17856,
-        "sha256": "a2ce492cb82034175208b60fec498c4bf9f2ef6c1e312ce51912c0a919e6514e"
+        "bytes": 17917,
+        "sha256": "0d9f9fa5669af7c8e64fa32cccde9c99d54a7bfa0fe4dd9d315eccdb0b06f585"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/sync_hf_publish_mirrors.py",
           "exists": true,
-          "bytes": 17856,
-          "sha256": "a2ce492cb82034175208b60fec498c4bf9f2ef6c1e312ce51912c0a919e6514e"
+          "bytes": 17917,
+          "sha256": "0d9f9fa5669af7c8e64fa32cccde9c99d54a7bfa0fe4dd9d315eccdb0b06f585"
         },
         "hf_model": {
           "path": "hf_model:scripts/sync_hf_publish_mirrors.py",
           "exists": true,
-          "bytes": 17856,
-          "sha256": "a2ce492cb82034175208b60fec498c4bf9f2ef6c1e312ce51912c0a919e6514e"
+          "bytes": 17917,
+          "sha256": "0d9f9fa5669af7c8e64fa32cccde9c99d54a7bfa0fe4dd9d315eccdb0b06f585"
         }
       },
       "failures": []
@@ -4535,39 +4560,39 @@
       "local": {
         "path": "repo:docs/index.html",
         "exists": true,
-        "bytes": 232536,
-        "sha256": "0eb22ba5498e9caefd2c7d6e70068a8a7e99ae32a4c91abef382c918d689d9bf"
+        "bytes": 232578,
+        "sha256": "e5427cec333219299cdac4069419918ccbb02db8f3c98e6b99cb69ff9895c0f3"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:index.html",
           "exists": true,
-          "bytes": 232536,
-          "sha256": "0eb22ba5498e9caefd2c7d6e70068a8a7e99ae32a4c91abef382c918d689d9bf"
+          "bytes": 232578,
+          "sha256": "e5427cec333219299cdac4069419918ccbb02db8f3c98e6b99cb69ff9895c0f3"
         },
         "hf_artifacts_root": {
           "path": "hf_artifacts:index.html",
           "exists": true,
-          "bytes": 232536,
-          "sha256": "0eb22ba5498e9caefd2c7d6e70068a8a7e99ae32a4c91abef382c918d689d9bf"
+          "bytes": 232578,
+          "sha256": "e5427cec333219299cdac4069419918ccbb02db8f3c98e6b99cb69ff9895c0f3"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/index.html",
           "exists": true,
-          "bytes": 232536,
-          "sha256": "0eb22ba5498e9caefd2c7d6e70068a8a7e99ae32a4c91abef382c918d689d9bf"
+          "bytes": 232578,
+          "sha256": "e5427cec333219299cdac4069419918ccbb02db8f3c98e6b99cb69ff9895c0f3"
         },
         "hf_model": {
           "path": "hf_model:index.html",
           "exists": true,
-          "bytes": 232536,
-          "sha256": "0eb22ba5498e9caefd2c7d6e70068a8a7e99ae32a4c91abef382c918d689d9bf"
+          "bytes": 232578,
+          "sha256": "e5427cec333219299cdac4069419918ccbb02db8f3c98e6b99cb69ff9895c0f3"
         },
         "hf_model_docs": {
           "path": "hf_model:docs/index.html",
           "exists": true,
-          "bytes": 232536,
-          "sha256": "0eb22ba5498e9caefd2c7d6e70068a8a7e99ae32a4c91abef382c918d689d9bf"
+          "bytes": 232578,
+          "sha256": "e5427cec333219299cdac4069419918ccbb02db8f3c98e6b99cb69ff9895c0f3"
         }
       },
       "failures": []
@@ -10591,6 +10616,254 @@
       },
       "failures": []
     },
+    {
+      "name": "results/omni_finetune/model_output_task_probes_20260616/RUN_REPORT.md",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/model_output_task_probes_20260616/RUN_REPORT.md",
+        "exists": true,
+        "bytes": 981,
+        "sha256": "73e9e0f52a47f56afd1d27ce9be33de9ffb89f52f35f34c1fc1c3ee7290c34b1"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/model_output_task_probes_20260616/RUN_REPORT.md",
+          "exists": true,
+          "bytes": 981,
+          "sha256": "73e9e0f52a47f56afd1d27ce9be33de9ffb89f52f35f34c1fc1c3ee7290c34b1"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/model_output_task_probes_20260616/RUN_REPORT.md",
+          "exists": true,
+          "bytes": 981,
+          "sha256": "73e9e0f52a47f56afd1d27ce9be33de9ffb89f52f35f34c1fc1c3ee7290c34b1"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/model_output_task_probes_20260616/RUN_REPORT.md",
+          "exists": true,
+          "bytes": 981,
+          "sha256": "73e9e0f52a47f56afd1d27ce9be33de9ffb89f52f35f34c1fc1c3ee7290c34b1"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
+        "exists": true,
+        "bytes": 21876,
+        "sha256": "3ca7045bf932afe1e3b32ad8183c90056538220fa814249b993e1d574695288b"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
+          "exists": true,
+          "bytes": 21876,
+          "sha256": "3ca7045bf932afe1e3b32ad8183c90056538220fa814249b993e1d574695288b"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
+          "exists": true,
+          "bytes": 21876,
+          "sha256": "3ca7045bf932afe1e3b32ad8183c90056538220fa814249b993e1d574695288b"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
+          "exists": true,
+          "bytes": 21876,
+          "sha256": "3ca7045bf932afe1e3b32ad8183c90056538220fa814249b993e1d574695288b"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/per_class_metrics.csv",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/per_class_metrics.csv",
+        "exists": true,
+        "bytes": 22569,
+        "sha256": "e5d85ed571b3647fab6dad7b46944a65981d57c51a87708cc5e86a20d71d1358"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/per_class_metrics.csv",
+          "exists": true,
+          "bytes": 22569,
+          "sha256": "e5d85ed571b3647fab6dad7b46944a65981d57c51a87708cc5e86a20d71d1358"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/per_class_metrics.csv",
+          "exists": true,
+          "bytes": 22569,
+          "sha256": "e5d85ed571b3647fab6dad7b46944a65981d57c51a87708cc5e86a20d71d1358"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/per_class_metrics.csv",
+          "exists": true,
+          "bytes": 22569,
+          "sha256": "e5d85ed571b3647fab6dad7b46944a65981d57c51a87708cc5e86a20d71d1358"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/predictions.csv",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/predictions.csv",
+        "exists": true,
+        "bytes": 176633,
+        "sha256": "c198bd15c3a5589d4de1da072cb70840d245993d43801e60ca4682a267e3dfeb"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/predictions.csv",
+          "exists": true,
+          "bytes": 176633,
+          "sha256": "c198bd15c3a5589d4de1da072cb70840d245993d43801e60ca4682a267e3dfeb"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/predictions.csv",
+          "exists": true,
+          "bytes": 176633,
+          "sha256": "c198bd15c3a5589d4de1da072cb70840d245993d43801e60ca4682a267e3dfeb"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/predictions.csv",
+          "exists": true,
+          "bytes": 176633,
+          "sha256": "c198bd15c3a5589d4de1da072cb70840d245993d43801e60ca4682a267e3dfeb"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
+        "exists": true,
+        "bytes": 169938,
+        "sha256": "d57137f78b67dc683fe29a7d3150f309384e58baa29938e8177b918359a0990c"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
+          "exists": true,
+          "bytes": 169938,
+          "sha256": "d57137f78b67dc683fe29a7d3150f309384e58baa29938e8177b918359a0990c"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
+          "exists": true,
+          "bytes": 169938,
+          "sha256": "d57137f78b67dc683fe29a7d3150f309384e58baa29938e8177b918359a0990c"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
+          "exists": true,
+          "bytes": 169938,
+          "sha256": "d57137f78b67dc683fe29a7d3150f309384e58baa29938e8177b918359a0990c"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/per_class_metrics.csv",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/per_class_metrics.csv",
+        "exists": true,
+        "bytes": 188619,
+        "sha256": "1f4b312a07a8e0a67a1cd6a83e2c83d0c91804f2d8a51c4eeda207444ae262e9"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/per_class_metrics.csv",
+          "exists": true,
+          "bytes": 188619,
+          "sha256": "1f4b312a07a8e0a67a1cd6a83e2c83d0c91804f2d8a51c4eeda207444ae262e9"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/per_class_metrics.csv",
+          "exists": true,
+          "bytes": 188619,
+          "sha256": "1f4b312a07a8e0a67a1cd6a83e2c83d0c91804f2d8a51c4eeda207444ae262e9"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/per_class_metrics.csv",
+          "exists": true,
+          "bytes": 188619,
+          "sha256": "1f4b312a07a8e0a67a1cd6a83e2c83d0c91804f2d8a51c4eeda207444ae262e9"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/predictions.csv",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/predictions.csv",
+        "exists": true,
+        "bytes": 1848188,
+        "sha256": "521edd5ce67341b1a4dba1dcf0f6e097ab9477536ef9cce96ec3bd0908c35469"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/predictions.csv",
+          "exists": true,
+          "bytes": 1848188,
+          "sha256": "521edd5ce67341b1a4dba1dcf0f6e097ab9477536ef9cce96ec3bd0908c35469"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/predictions.csv",
+          "exists": true,
+          "bytes": 1848188,
+          "sha256": "521edd5ce67341b1a4dba1dcf0f6e097ab9477536ef9cce96ec3bd0908c35469"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/predictions.csv",
+          "exists": true,
+          "bytes": 1848188,
+          "sha256": "521edd5ce67341b1a4dba1dcf0f6e097ab9477536ef9cce96ec3bd0908c35469"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "results/omni_finetune/model_output_task_probes_20260616/summary.json",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/model_output_task_probes_20260616/summary.json",
+        "exists": true,
+        "bytes": 2000,
+        "sha256": "de95421d93fec5d12049e492db9fbe7c10af5c2cd0d1039da82c05ec82bf98c5"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/model_output_task_probes_20260616/summary.json",
+          "exists": true,
+          "bytes": 2000,
+          "sha256": "de95421d93fec5d12049e492db9fbe7c10af5c2cd0d1039da82c05ec82bf98c5"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/model_output_task_probes_20260616/summary.json",
+          "exists": true,
+          "bytes": 2000,
+          "sha256": "de95421d93fec5d12049e492db9fbe7c10af5c2cd0d1039da82c05ec82bf98c5"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/model_output_task_probes_20260616/summary.json",
+          "exists": true,
+          "bytes": 2000,
+          "sha256": "de95421d93fec5d12049e492db9fbe7c10af5c2cd0d1039da82c05ec82bf98c5"
+        }
+      },
+      "failures": []
+    },
     {
       "name": "results/omni_finetune/multi_episode_128_task_baselines/BASELINE_ALIGNMENT_REPORT.md",
       "status": "pass",
@@ -18533,27 +18806,27 @@
       "local": {
         "path": "repo:TASK_METHOD_20_GAP_AUDIT.md",
         "exists": true,
-        "bytes": 16600,
-        "sha256": "e6bd5b49d01eb095fe6f0d38436e08f2c2ff1a4449f98a08928d51e965e563bb"
+        "bytes": 16234,
+        "sha256": "351e55637374770221115486fd6ef46550ae923c4fae5c01d3bb1e777b5a44fb"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:TASK_METHOD_20_GAP_AUDIT.md",
           "exists": true,
-          "bytes": 16600,
-          "sha256": "e6bd5b49d01eb095fe6f0d38436e08f2c2ff1a4449f98a08928d51e965e563bb"
+          "bytes": 16234,
+          "sha256": "351e55637374770221115486fd6ef46550ae923c4fae5c01d3bb1e777b5a44fb"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:TASK_METHOD_20_GAP_AUDIT.md",
           "exists": true,
-          "bytes": 16600,
-          "sha256": "e6bd5b49d01eb095fe6f0d38436e08f2c2ff1a4449f98a08928d51e965e563bb"
+          "bytes": 16234,
+          "sha256": "351e55637374770221115486fd6ef46550ae923c4fae5c01d3bb1e777b5a44fb"
         },
         "hf_model": {
           "path": "hf_model:TASK_METHOD_20_GAP_AUDIT.md",
           "exists": true,
-          "bytes": 16600,
-          "sha256": "e6bd5b49d01eb095fe6f0d38436e08f2c2ff1a4449f98a08928d51e965e563bb"
+          "bytes": 16234,
+          "sha256": "351e55637374770221115486fd6ef46550ae923c4fae5c01d3bb1e777b5a44fb"
         }
       },
       "failures": []
@@ -18564,27 +18837,27 @@
       "local": {
         "path": "repo:TASK_METHOD_20_RESULT_MATRIX.md",
         "exists": true,
-        "bytes": 4224,
-        "sha256": "fe14a0e1709a8bb5b9fb1fd720ffde0aecfed578329d8e1e71b352a83b23b1f8"
+        "bytes": 4208,
+        "sha256": "bfe01b258fe121448d2b5b188c6995041c81d7ce1286dcd2ee0bf9c01d6a6193"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 4224,
-          "sha256": "fe14a0e1709a8bb5b9fb1fd720ffde0aecfed578329d8e1e71b352a83b23b1f8"
+          "bytes": 4208,
+          "sha256": "bfe01b258fe121448d2b5b188c6995041c81d7ce1286dcd2ee0bf9c01d6a6193"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 4224,
-          "sha256": "fe14a0e1709a8bb5b9fb1fd720ffde0aecfed578329d8e1e71b352a83b23b1f8"
+          "bytes": 4208,
+          "sha256": "bfe01b258fe121448d2b5b188c6995041c81d7ce1286dcd2ee0bf9c01d6a6193"
         },
         "hf_model": {
           "path": "hf_model:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 4224,
-          "sha256": "fe14a0e1709a8bb5b9fb1fd720ffde0aecfed578329d8e1e71b352a83b23b1f8"
+          "bytes": 4208,
+          "sha256": "bfe01b258fe121448d2b5b188c6995041c81d7ce1286dcd2ee0bf9c01d6a6193"
         }
       },
       "failures": []

docs/data/public_surface_qa.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Public Project Surface",
   "status": "pass",
-  "generated_at_utc": "2026-06-16T12:04:40+00:00",
+  "generated_at_utc": "2026-06-16T13:36:07+00:00",
   "scope": "Repo README, GitHub Pages HTML, Hugging Face Space card, artifact dataset card, and model card.",
   "checks": [
     {
@@ -18,7 +18,7 @@
         "website_integrity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-16T12:01:39+00:00"
+          "generated_at_utc": "2026-06-16T13:35:52+00:00"
         },
         "rendered_site_check": {
           "exists": true,
@@ -28,27 +28,27 @@
         "task_surface_integrity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-16T12:01:37+00:00"
+          "generated_at_utc": "2026-06-16T13:35:48+00:00"
         },
         "source_alignment": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-16T12:01:37+00:00"
+          "generated_at_utc": "2026-06-16T13:35:47+00:00"
         },
         "scale_up_status": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-16T12:01:40+00:00"
+          "generated_at_utc": "2026-06-16T13:35:51+00:00"
         },
         "publication_package": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-16T12:04:24+00:00"
+          "generated_at_utc": "2026-06-16T13:36:07+00:00"
         },
         "mirror_parity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-16T12:03:33+00:00"
+          "generated_at_utc": "2026-06-16T13:35:58+00:00"
         }
       },
       "failures": {}

docs/data/publication_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-16T12:04:24+00:00",
+  "generated_at_utc": "2026-06-16T13:36:07+00:00",
   "checks": [
     {
       "name": "required_publication_assets_present",
@@ -200,8 +200,8 @@
     "github_repo": {
       "root": "repo",
       "exists": true,
-      "file_count": 1196,
-      "text_file_count": 1001,
+      "file_count": 1205,
+      "text_file_count": 1010,
       "largest_file": {
         "path": "results/episode_task_suite/modality_reconstruction/predictions.npz",
         "bytes": 55702978
@@ -211,8 +211,8 @@
     "hf_space_bundle": {
       "root": "hf_publish/space",
       "exists": true,
-      "file_count": 976,
-      "text_file_count": 820,
+      "file_count": 984,
+      "text_file_count": 828,
       "largest_file": {
         "path": "results/episode_task_suite/modality_reconstruction/predictions.npz",
         "bytes": 55702978
@@ -222,8 +222,8 @@
     "hf_artifact_bundle": {
       "root": "hf_publish/artifacts",
       "exists": true,
-      "file_count": 2314,
-      "text_file_count": 1008,
+      "file_count": 2331,
+      "text_file_count": 1017,
       "largest_file": {
         "path": "results/episode_task_suite/modality_reconstruction/predictions.npz",
         "bytes": 55702978
@@ -233,8 +233,8 @@
     "hf_model_bundle": {
       "root": "hf_publish/model",
       "exists": true,
-      "file_count": 2746,
-      "text_file_count": 1168,
+      "file_count": 2764,
+      "text_file_count": 1177,
       "largest_file": {
         "path": "pytorch_model.bin",
         "bytes": 93495480

docs/data/quality_gates.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Release Checks",
   "status": "pass",
-  "generated_at_utc": "2026-06-16T12:04:40+00:00",
+  "generated_at_utc": "2026-06-16T13:36:07+00:00",
   "rule": "A release is current when the automated reports pass and the live GitHub/Hugging Face mirrors are verified after publishing.",
   "automated_gates": [
     {

docs/data/scope_claims_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-16T12:01:40+00:00",
+  "generated_at_utc": "2026-06-16T13:35:51+00:00",
   "summary": {
     "qwen3_omni_verified_diagnostic_pilot": true,
     "dataset_manifest_num_episodes": 119,

docs/data/single_episode_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "Single-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-16T11:26:57+00:00",
+  "generated_at_utc": "2026-06-16T13:35:38+00:00",
   "description": "Minimal and Neural MLP baselines on the one public sample episode, both scored on all 20 task contracts.",
   "task_count": 20,
   "method_count": 2,

docs/data/source_alignment_audit.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Source Alignment Note",
   "status": "pass",
-  "generated_at_utc": "2026-06-16T12:01:37+00:00",
+  "generated_at_utc": "2026-06-16T13:35:47+00:00",
   "alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
   "alignment_summary": {
     "full_dataset_repo": "ropedia-ai/xperience-10m",

docs/data/task_method_20_result_matrix.json

@@ -1,11 +1,11 @@
 {
   "title": "Task Method 20-Result Matrix",
   "status": "pass",
-  "generated_at_utc": "2026-06-16T11:26:57+00:00",
+  "generated_at_utc": "2026-06-16T13:35:38+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
-  "scored_method_task_count": 111,
+  "scored_method_task_count": 113,
   "series": [
     {
       "id": "minimal",
@@ -158,20 +158,20 @@
       "kind": "partial_128_episode_foundation_model_overlay",
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
-      "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics on task-aligned JSON outputs.",
+      "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 scored from existing verified action/object JSON.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 6,
-      "covered_task_count": 6,
+      "scored_task_count": 7,
+      "covered_task_count": 7,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 14,
+      "scoreless_task_count": 13,
       "unsupported_task_count": 0,
-      "not_evaluated_task_count": 14,
+      "not_evaluated_task_count": 13,
       "status_counts": {
-        "not_evaluated_in_verified_package": 14,
-        "scored": 6
+        "not_evaluated_in_verified_package": 13,
+        "scored": 7
       },
-      "coverage_fraction": 0.3,
+      "coverage_fraction": 0.35,
       "result_record_fraction": 1.0
     },
     {
@@ -182,20 +182,20 @@
       "kind": "partial_128_episode_foundation_model_overlay",
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
-      "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation.",
+      "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 16 scored from existing verified action/object JSON.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 6,
-      "covered_task_count": 6,
+      "scored_task_count": 7,
+      "covered_task_count": 7,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 14,
+      "scoreless_task_count": 13,
       "unsupported_task_count": 0,
-      "not_evaluated_task_count": 14,
+      "not_evaluated_task_count": 13,
       "status_counts": {
-        "not_evaluated_in_verified_package": 14,
-        "scored": 6
+        "not_evaluated_in_verified_package": 13,
+        "scored": 7
       },
-      "coverage_fraction": 0.3,
+      "coverage_fraction": 0.35,
       "result_record_fraction": 1.0
     },
     {
@@ -2768,17 +2768,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "qwen3_omni_v6_lora",
       "method": "Qwen3-Omni v6 LoRA",
-      "status": "not_evaluated_in_verified_package",
-      "status_label": "not evaluated",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
-      "metric_key": "macro_f1",
-      "source": null,
+      "raw": 0.0002220083079671497,
+      "raw_text": "0.0002",
+      "normalized_score": 0.0002220083079671497,
+      "metric_key": "action_object_relation_macro_f1",
+      "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
       "scope": "multi_episode_128_partial_model_overlay",
-      "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"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -2786,17 +2786,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "cosmos3_super_reasoner",
       "method": "Cosmos3-Super Reasoner",
-      "status": "not_evaluated_in_verified_package",
-      "status_label": "not evaluated",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
-      "metric_key": "macro_f1",
-      "source": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
+      "metric_key": "action_object_relation_macro_f1",
+      "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
       "scope": "multi_episode_128_partial_model_overlay",
-      "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"
+      "reason": null
     },
     {
       "task_number": 16,

docs/data/task_surface_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-16T12:01:37+00:00",
+  "generated_at_utc": "2026-06-16T13:35:48+00:00",
   "summary": {
     "task_count": 12,
     "expected_task_count": 12,

docs/data/unified_task_model_radar.json

@@ -1,11 +1,11 @@
 {
   "title": "Unified 20-Task Model Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-16T11:26:57+00:00",
+  "generated_at_utc": "2026-06-16T13:35:38+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
-  "scored_method_task_count": 111,
+  "scored_method_task_count": 113,
   "normalization_policy": {
     "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
     "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -167,20 +167,20 @@
       "kind": "partial_128_episode_foundation_model_overlay",
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
-      "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics on task-aligned JSON outputs.",
+      "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 scored from existing verified action/object JSON.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 6,
-      "covered_task_count": 6,
+      "scored_task_count": 7,
+      "covered_task_count": 7,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 14,
+      "scoreless_task_count": 13,
       "unsupported_task_count": 0,
-      "not_evaluated_task_count": 14,
+      "not_evaluated_task_count": 13,
       "status_counts": {
-        "not_evaluated_in_verified_package": 14,
-        "scored": 6
+        "not_evaluated_in_verified_package": 13,
+        "scored": 7
       },
-      "coverage_fraction": 0.3,
+      "coverage_fraction": 0.35,
       "result_record_fraction": 1.0
     },
     {
@@ -191,20 +191,20 @@
       "kind": "partial_128_episode_foundation_model_overlay",
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
-      "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation.",
+      "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 16 scored from existing verified action/object JSON.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 6,
-      "covered_task_count": 6,
+      "scored_task_count": 7,
+      "covered_task_count": 7,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 14,
+      "scoreless_task_count": 13,
       "unsupported_task_count": 0,
-      "not_evaluated_task_count": 14,
+      "not_evaluated_task_count": 13,
       "status_counts": {
-        "not_evaluated_in_verified_package": 14,
-        "scored": 6
+        "not_evaluated_in_verified_package": 13,
+        "scored": 7
       },
-      "coverage_fraction": 0.3,
+      "coverage_fraction": 0.35,
       "result_record_fraction": 1.0
     },
     {
@@ -1930,6 +1930,28 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
+        "qwen3_omni_v6_lora": {
+          "raw": 0.0002220083079671497,
+          "metric_key": "action_object_relation_macro_f1",
+          "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
+          "scope": "multi_episode_128_partial_model_overlay",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0002220083079671497,
+          "raw_text": "0.0002",
+          "status_label": "scored"
+        },
+        "cosmos3_super_reasoner": {
+          "raw": 0.0,
+          "metric_key": "action_object_relation_macro_f1",
+          "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
+          "scope": "multi_episode_128_partial_model_overlay",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0,
           "metric_key": "macro_f1",
@@ -1974,28 +1996,6 @@
           "raw_text": "n/a",
           "status_label": "not supported"
         },
-        "qwen3_omni_v6_lora": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_partial_model_overlay",
-          "status": "not_evaluated_in_verified_package",
-          "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",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not evaluated"
-        },
-        "cosmos3_super_reasoner": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_partial_model_overlay",
-          "status": "not_evaluated_in_verified_package",
-          "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",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not evaluated"
-        },
         "cosmos3_nano_future_window": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -2492,7 +2492,7 @@
       "title": "Qwen3-Omni v6 LoRA",
       "status": "verified",
       "task_aligned_axes": "Qwen3",
-      "coverage": "20 records / 6 scored task-aligned axes",
+      "coverage": "20 records / 7 scored task-aligned axes",
       "headline": "JSON validity 0.9990; action macro-F1 0.0029",
       "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json"
     },
@@ -2500,7 +2500,7 @@
       "id": "cosmos3_super_reasoner",
       "title": "Cosmos3-Super Reasoner",
       "status": "verified_base_weight_eval",
-      "coverage": "20 records / 6 scored task-aligned axes",
+      "coverage": "20 records / 7 scored task-aligned axes",
       "headline": "JSON validity 0.5112; action macro-F1 0.0008",
       "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json"
     },
@@ -5066,17 +5066,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "qwen3_omni_v6_lora",
       "method": "Qwen3-Omni v6 LoRA",
-      "status": "not_evaluated_in_verified_package",
-      "status_label": "not evaluated",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
-      "metric_key": "macro_f1",
-      "source": null,
+      "raw": 0.0002220083079671497,
+      "raw_text": "0.0002",
+      "normalized_score": 0.0002220083079671497,
+      "metric_key": "action_object_relation_macro_f1",
+      "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
       "scope": "multi_episode_128_partial_model_overlay",
-      "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"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -5084,17 +5084,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "cosmos3_super_reasoner",
       "method": "Cosmos3-Super Reasoner",
-      "status": "not_evaluated_in_verified_package",
-      "status_label": "not evaluated",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
-      "metric_key": "macro_f1",
-      "source": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
+      "metric_key": "action_object_relation_macro_f1",
+      "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
       "scope": "multi_episode_128_partial_model_overlay",
-      "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"
+      "reason": null
     },
     {
       "task_number": 16,

results/omni_finetune/model_output_task_probes_20260616/RUN_REPORT.md

@@ -0,0 +1,13 @@
+# Existing Model-Output Task Probes
+
+Generated: `2026-06-16T13:35:37+00:00`
+
+This package scores only task targets already present in verified held-out
+prediction JSON. It does not run new inference and does not infer targets that
+are absent from a model branch.
+
+| Method | ID | Status | Scored rows | Task 16 macro-F1 | Evidence |
+| --- | --- | --- | ---: | ---: | --- |
+| Qwen3-Omni v6 LoRA | qwen3_omni_v6_lora | scored | 4014 | 0.000222 | results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/predictions.jsonl |
+| Cosmos3-Super Reasoner | cosmos3_super_reasoner | scored | 446 | 0.000000 | results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/predictions.jsonl |
+| Cosmos3-Nano Future Window | cosmos3_nano_future_window | unsupported_without_required_fields | n/a | n/a | verified future-window predictions do not contain object-set fields |

results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json

@@ -0,0 +1,320 @@
+{
+  "accuracy": 0.0,
+  "action_object_relation_accuracy": 0.0,
+  "action_object_relation_macro_f1": 0.0,
+  "artifact_files": {
+    "metrics_json": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
+    "per_class_metrics_csv": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/per_class_metrics.csv",
+    "predictions_csv": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/predictions.csv"
+  },
+  "excluded_rows_without_true_relation": 2,
+  "generated_at_utc": "2026-06-16T13:35:37+00:00",
+  "labels": [
+    "Adjust canned food on shelf :: canned food | cardboard box | store shelf",
+    "Adjust item on shelf :: shelf | stationery package",
+    "Adjust lantern shape :: red pleated paper lantern",
+    "Adjust lantern string :: red paper lantern | string",
+    "Adjust paper :: cardboard square | paper | pen | star beads",
+    "Adjust pot position :: pot",
+    "Adjust puzzle piece :: jigsaw puzzle | puzzle box | puzzle pieces",
+    "Align canned food on shelf :: canned food | cardboard box | retail shelf",
+    "Align edges of paper lantern :: hands | red paper lantern",
+    "Align paper lantern edges :: hands | red paper lantern",
+    "Apply adhesive tape to lantern :: adhesive tape | red paper lantern",
+    "Approach boxes :: cardboard boxes | colleague | shelving unit",
+    "Approaching and pressing the door switch :: glass door | switch | wall",
+    "Approaching the table :: beads | chairs | table",
+    "Arrange buttons :: red buttons | smartphone | table",
+    "Arrange buttons in a line :: buttons | phone | table",
+    "Arrange star beads :: paper | pen | power bank | smartphone | star beads",
+    "Arrange star beads for counting :: paper | pen | star beads",
+    "Attempt to fit puzzle piece :: puzzle board | puzzle piece",
+    "Attempt to fit puzzle piece :: puzzle piece",
+    "Bend and manipulate plastic strip :: plastic strip | stationary box | table | water bottle",
+    "Browse smartphone screen :: paper strips | smartphone | star ornaments",
+    "Bundle display hooks :: container | display hooks",
+    "Closing the door :: door | dustpan",
+    "Counting and organizing beads :: cardboard squares | paper | pen | star-shaped beads",
+    "Counting star beads :: paper | pen | star beads",
+    "Cut along the marked line :: cardboard | hand | utility knife",
+    "Cut cardboard :: cardboard | desk | pen | ruler | utility knife",
+    "Cut cardboard piece :: cardboard strip | scissors",
+    "Entering the VR training room :: doorway | person | table",
+    "Expand paper lantern :: adhesive tape roll | cardboard box | red paper lantern",
+    "Extract wire hangers from box :: cardboard box | wire hangers",
+    "Fold paper lantern :: red paper honeycomb lantern",
+    "Fold plastic strip :: container with tools | purple plastic strip | water bottle | white table",
+    "Gather star beads :: cardboard squares | mobile phone | paper | pen | power bank | star beads",
+    "Gesturing :: cardboard pieces | marker | pencil case | ruler | scissors",
+    "Grasp cleaning bottle :: bowls | chopping board | cleaning fluid bottle",
+    "Grasp lantern :: red paper honeycomb lantern",
+    "Grasp lantern component :: cardboard box | paper lantern | tape",
+    "Grasping cleaning cloth :: cleaning cloth | countertop",
+    "Greeting/acknowledging participants :: person | table | vr headset",
+    "Handle paper lantern component :: cardboard box | paper lantern component | plastic bag | red paper lantern",
+    "Hold and bend plastic strip :: bottle | purple plastic strip | stationery box",
+    "Hold and manipulate paper strip :: beads | mobile phone | power bank | yellow paper strip",
+    "Hold beads :: paper | pen | power bank | smartphone | star-shaped beads",
+    "Hold canned food :: box of cans | can of soup | shelf",
+    "Hold cardboard piece :: cardboard pieces | marker | pencil case | ruler | scissors",
+    "Hold container lid :: dustpan | red plastic container lid",
+    "Hold paper lantern :: red paper lantern | sofa",
+    "Hold smartphone :: kettle | kitchen counter | sink | smartphone",
+    "Hold smartphone :: quilling paper strips | small blue beads | smartphone",
+    "Identify next cardboard piece :: cardboard pieces | marker",
+    "Inspect shelf condition :: colleague | shelf",
+    "Interact with smartphone :: beads | smartphone | yellow paper strip",
+    "Interact with smartphone :: cans | shelf | smartphone",
+    "Lift pot lid :: pot | pot lid",
+    "Manipulate adhesive strip :: adhesive strip | paper sheets | puzzle box | smartphone | water bottle",
+    "Manipulate bead :: bead piles | container | paper strips | yellow bead",
+    "Manipulate beads :: blue beads | power bank | smartphone | yellow beads",
+    "Manipulate craft paper strips :: paper strips | scissors | smartphone",
+    "Manipulate craft piece :: craft pieces | scissors | smartphone",
+    "Manipulate material :: blue crafting material | hand",
+    "Manipulate paper decoration :: paper cone | paper decoration | smartphone | water bottle",
+    "Manipulate paper edge :: hands | paper cone | puzzle box | smartphone | water bottle",
+    "Manipulate paper strip :: container with tools | table | yellow paper strip",
+    "Manipulate paper strip :: craft materials | purple paper strip | scissors | smartphone",
+    "Manipulate paper strip :: paper cone | paper strip | puzzle box | smartphone | water bottle",
+    "Manipulate paper strip :: purple paper strip | quilling paper pile | smartphone",
+    "Manipulate plastic strip :: purple plastic strip | storage bin | water bottle",
+    "Manipulate plastic strips :: desk | plastic strips | water bottle",
+    "Manipulate puzzle piece :: jigsaw puzzle | puzzle piece",
+    "Manipulate puzzle pieces :: puzzle box | puzzle mat | puzzle pieces",
+    "Manipulate yellow strip :: beads | cell phone | pen | yellow strip",
+    "Manipulating paper strips :: beads | blue paper strip | yellow paper strip",
+    "Mark cardboard piece :: cardboard piece | marker",
+    "Mark cardboard piece :: cardboard piece | marker | pouch",
+    "Marking cardboard piece :: cardboard pieces | marker | ruler | scissors",
+    "Move dustpan to side :: dustpan",
+    "Move hand away :: canned food | retail shelf",
+    "Move hand away from shelf :: canned food | cardboard box | store shelf",
+    "Move marker and adjust hand :: cardboard pieces | marker",
+    "Move phone :: cardboard | smartphone | utility knife",
+    "Move pot :: faucet | pot | sink",
+    "Move smartphone :: craft beads | paper strips | smartphone",
+    "Move through aisle :: aisle floor | display hooks | metal shelving units",
+    "Move through the training room :: chairs | fire extinguisher | tables | vr headsets",
+    "Move to shelf :: cardboard box | colleague | shelves",
+    "Move towards kitchen area :: cloth | sink",
+    "Move towards the stove :: blue bowl | faucet | metal container | red bowl | sink",
+    "Observe and pause :: cardboard pieces | marker | pencil case | ruler | scissors",
+    "Observe and walk through store :: colleague | inventory boxes | shelves",
+    "Observe colleague and workspace :: price tag | shelves | watch",
+    "Observe puzzle progress :: hand | jigsaw puzzle",
+    "Observe workspace :: cardboard boxes | colleague | shelving unit",
+    "Open earbud case :: earbud case",
+    "Open folded paper lantern :: cardboard box | red pleated paper lantern",
+    "Open paper lantern :: red paper honeycomb lantern",
+    "Open paper lantern component :: paper lantern component",
+    "Open stove pot lid :: blue bowl | cloth | faucet | red bowl | sink | soap dispenser | white bowl",
+    "Operate smartphone :: craft paper strips | folded paper fan | smartphone",
+    "Organize cardboard pieces :: cardboard pieces | marker | pencil case | ruler | scissors",
+    "Pick up button :: buttons | table",
+    "Pick up can :: canned food | cardboard box",
+    "Pick up canned food :: canned food | cardboard box",
+    "Pick up dustpan :: dustpan | smartphone",
+    "Pick up items from the shopping bag :: cardboard boxes | red shopping bag | retail shelf",
+    "Pick up new cardboard piece :: cardboard piece | marker",
+    "Pick up packaged paper lantern component :: cardboard box | packaged paper lantern component",
+    "Pick up pen :: paper | pen | star beads",
+    "Pick up puzzle piece :: jigsaw puzzle | puzzle piece",
+    "Pick up small piece of material :: blue crafting material | hand",
+    "Pick up smartphone :: cans | shelf | smartphone",
+    "Pick up star bead :: cardboard squares | mobile phone | paper | pen | power bank | star beads",
+    "Pick up utility knife :: cardboard | utility knife",
+    "Picking up bottle :: bottle",
+    "Picking up crafting material :: beads | papers | pen | table",
+    "Place and count bead :: paper | pen | star beads",
+    "Place another canned food on shelf :: box | canned food",
+    "Place button :: buttons | hand | smartphone | table",
+    "Place button :: buttons | hand | table",
+    "Place can on shelf :: canned food | retail shelf",
+    "Place canned food on shelf :: can of vegetables | cardboard boxes | store shelf",
+    "Place cloth on floor :: cloth",
+    "Place hand on table :: craft beads | paper strips | smartphone",
+    "Place item on shelf :: stationery package",
+    "Place items on the shelf :: packaged items | retail shelf",
+    "Place lid back :: pot | pot lid",
+    "Place marked piece down :: cardboard piece | marker",
+    "Place material :: bead design | blue crafting material | hand",
+    "Place phone down :: beads | pencil holder | smartphone | yellow paper strip",
+    "Place piece into puzzle :: jigsaw puzzle | puzzle piece",
+    "Place puzzle piece :: puzzle board | puzzle piece",
+    "Place smartphone down :: power bank | quilling paper strips | small paper stars | smartphone",
+    "Place smartphone down :: quilling paper strips | small paper stars | smartphone",
+    "Place smartphone on stand :: saucepan | smartphone | smartphone stand | yellow jacket",
+    "Place towel :: pot | towel",
+    "Placing paper strip :: adhesive strip | paper cone | phone",
+    "Placing paper strip :: paper cone | phone | puzzle box | water bottle",
+    "Preparing to craft :: beads | chairs | table",
+    "Put down smartphone :: paper stars | paper strips | smartphone",
+    "Put down smartphone :: power bank | smartphone",
+    "Reach for another item :: item | shelf",
+    "Reach for cleaning supplies :: bowls | chopping board | cleaning fluid bottle",
+    "Reach for craft items :: smartphone | star-shaped craft items | table",
+    "Reach for next can :: can of vegetables | cardboard boxes | store shelf",
+    "Reach for next canned food :: box | canned food | retail shelf",
+    "Reach for next item :: packaged item | shelf",
+    "Reach for puzzle piece :: puzzle board | puzzle box | puzzle pieces",
+    "Reach for wire hangers :: cardboard box | wire hangers",
+    "Reach into box :: box of cans",
+    "Record count :: paper | pen | star-shaped beads",
+    "Release cardboard piece and gesture :: cardboard piece | cardboard piles | marker | pouch | ruler | scissors",
+    "Release hook :: display hook",
+    "Release lantern :: red paper lantern",
+    "Release paper strip :: craft beads | paper strip | scissors | smartphone",
+    "Release puzzle piece :: jigsaw puzzle | puzzle box | puzzle pieces",
+    "Release scissors :: craft paper strips | folded paper fan | scissors | smartphone",
+    "Release smartphone :: paper scraps | scissors | smartphone | table",
+    "Remove cleaning bottle :: cleaning bottle | plastic bowls",
+    "Remove paper lantern part from packaging :: paper lantern | red hand fan",
+    "Remove plastic packaging :: packaging | paper lantern component",
+    "Reposition hand :: cardboard | utility knife",
+    "Resume observation :: cardboard pieces | marker | pencil case | ruler | scissors",
+    "Retrieve canned food from box :: box | canned food",
+    "Retrieve next canned food item :: canned food | cardboard box",
+    "Retrieving more beads :: paper | pen | star beads",
+    "Rinse cloth in sink :: cloth | sink | water faucet",
+    "Scroll smartphone screen :: paper stars | paper strips | smartphone",
+    "Search for puzzle piece :: jigsaw puzzle | puzzle pieces",
+    "Secure paper edges with adhesive :: adhesive strip | paper cone pieces | puzzle box | smartphone | water bottle",
+    "Securing paper structure :: decorative stars | paper strips | smartphone | water bottle",
+    "Sort and adjust button line :: buttons | smartphone | table",
+    "Sort and arrange buttons :: buttons | smartphones | soda can | table",
+    "Sort and count beads :: paper | pen | star beads",
+    "Sort and place buttons :: buttons | coca-cola can | smartphone",
+    "Sort beads :: paper | pen | smartphone | star-shaped beads",
+    "Sort beads and write count :: paper | pen | power bank | smartphone | star-shaped beads",
+    "Sort button :: buttons | cell phone",
+    "Sort buttons :: buttons | table",
+    "Sort craft items :: star-shaped craft items | table",
+    "Sort puzzle pieces :: jigsaw puzzle pieces | table",
+    "Sort small craft pieces :: paper strips | scissors | smartphone | star-shaped craft pieces",
+    "Sort star-shaped beads :: marker | mobile phone | paper | power bank | star-shaped beads",
+    "Start cutting :: cardboard | utility knife",
+    "Stir contents :: cooking utensil | pot",
+    "Use phone :: beads | paper | power bank | smartphone",
+    "Use phone while crafting :: beads | pencil holder | smartphone | yellow paper strip",
+    "Use smartphone :: buttons | chair | smartphone | table",
+    "Use smartphone :: buttons | smartphone | table",
+    "Use smartphone :: charging cable | paper strips | power bank | smartphone | star-shaped paper crafts",
+    "Use smartphone :: containers | kettle | kitchen counter | rice cooker | smartphone",
+    "Walk towards other aisles :: retail store aisle",
+    "Walk towards shelves :: cardboard boxes | red bin | shelving unit",
+    "Walking across the room :: chair | fire extinguisher | office | table",
+    "Walking in the hallway :: hallway | people | tables | vr headsets",
+    "Walking towards door :: door | dustpan",
+    "Washing hands in sink :: faucet | sink",
+    "Wipe kitchen counter :: door | laundry basket | mop",
+    "Wiping countertop :: cleaning cloth | countertop",
+    "Write count on paper :: marker | mobile phone | paper | power bank | star-shaped beads",
+    "Write on paper :: cardboard square | paper | pen | star beads",
+    "sort craft materials :: paper pieces | scissors | smartphone",
+    "Pick up and place canned goods on shelf :: bin | canned goods | shelf",
+    "Browsing smartphone content :: smartphone",
+    "Place item on shelf :: retail item | shelf",
+    "Place item on shelf :: canned food | shelf",
+    "<missing_pred_relation>",
+    "Approach packing area :: items to pack | packing area",
+    "Approach restocking supplies :: aisle | restocking supplies | shelf",
+    "unknown :: unknown",
+    "Approach table :: materials | table | tools | work surface",
+    "Place item in container :: canned goods | plastic container | shopping bag",
+    "Pick up canned food :: canned food | shelf",
+    "Adjusting items on the shelf :: items | shelf",
+    "Wipe hands :: hands | sink | water bottle",
+    "Approach the stove :: cooking pot | kitchen counter | stove",
+    "Place item on shelf :: plush toy | shelf",
+    "Place item on shelf :: canned goods | shelf",
+    "Adjust cardboard :: cardboard pieces | workspace surface",
+    "Adjust cardboard :: cardboard | cutting mat | glue stick | marker | measuring tape | ruler | scissors | work table",
+    "Approach packing area :: cardboard pieces | marker | ruler | scissors | work table",
+    "Adjust cardboard :: cardboard piece | marker | ruler | workspace surface",
+    "Adjust cardboard position :: cardboard piece | marker | ruler | scissors | work surface",
+    "Adjust cardboard position :: cardboard piece | hands | work surface",
+    "Adjust cardboard :: cardboard piece | glue stick | marker | measuring tape | pencil | ruler | scissors | work table",
+    "Adjust cardboard :: cardboard | glue stick | marker | measuring tape | pencil | ruler | scissors | work table",
+    "Adjust cardboard position :: cardboard piece | scissors | work table",
+    "Adjust cardboard position :: cardboard piece | scissors | work surface",
+    "Cut cardboard with utility knife :: cardboard | ruler | table | utility knife",
+    "Cut cardboard :: cardboard | glue | marker | measuring tape | pen | ruler | scissors | work surface",
+    "Adjusting items on shelf :: containers | retail items | shelf",
+    "Approach packing area :: container | items to pack | packing area",
+    "Adjust cardboard divider :: cardboard divider | retail items | shelf",
+    "Adjusting items on shelf :: retail items | shelf",
+    "Approach packing area :: boxes | items to pack | packing area",
+    "Adjust grip :: canned food | plastic container | shelf",
+    "Adjust item on shelf :: retail items | shelf",
+    "Approach packing area :: cardboard pieces | packing area | storage bins",
+    "Adjust cardboard position :: cardboard pieces | scissors | table surface",
+    "Adjust cardboard divider :: cardboard divider | cardboard pieces | table surface",
+    "Adjust cardboard divider :: cardboard divider | cardboard pieces | scissors | table",
+    "Place canned food on shelf :: canned food | shelf",
+    "Pick up canned food :: bin | canned food | shelf",
+    "Pick up canned food :: box | canned food | shelf",
+    "Pick up canned food :: canned food | container | shelf",
+    "Adjust canned food on shelf :: canned food | shelf",
+    "Move along the shelf :: retail items | shelf",
+    "Picking up and placing canned goods :: canned goods | shelf",
+    "Move along the shelf :: canned goods | plastic container | shelf",
+    "Adjust item on shelf :: retail item | shelf",
+    "Browsing smartphone content :: retail items | shelf | smartphone",
+    "Manipulate paper strip :: paper strip | scissors | table",
+    "Manipulate paper strip :: marker | paper strip | pink cloth | ruler | scissors | smartphone | table | water bottle",
+    "Adjust grip :: hand | red container",
+    "Approach packing area :: boxes | packaging materials | red hat | table",
+    "Approach packing area :: boxes | packaging materials | red cap | table",
+    "Manipulate paper strip :: paper strip",
+    "Adjust lantern string :: handle | lantern | string",
+    "Adjust grip :: lid | red container",
+    "Approach packing area :: items to pack | packing area | packing materials",
+    "Adjust lantern string :: lantern handle | lantern string | paper lantern",
+    "Adjust grip :: red container | small white object",
+    "Adjust lantern string :: handle component | paper lantern | string",
+    "Approach table :: people | table",
+    "Approach table :: items on table | people | table",
+    "Adjust Mahjong tile :: mahjong tile | mahjong tile stack | table surface",
+    "Adjusting and placing down paper pieces :: hand | paper pieces | table",
+    "Approach table :: cardboard | chair | mahjong tiles | marker | paper | ruler | scissors | table",
+    "Approach table :: beads | cardboard | marker | paper | pen | ruler | scissors | table",
+    "Manipulate paper strip :: craft materials | hands | marker | paper strip | ruler | scissors | table | workspace",
+    "Manipulate paper strip :: craft materials | glue | hands | marker | paper strip | ruler | scissors | table",
+    "Adjust bead piles :: beads | table",
+    "Manipulate paper strip :: beads | glue | marker | paper strip | ruler | scissors | smartphone | table",
+    "Manipulate paper strip :: beads | mahjong tiles | marker | paper strip | ruler | scissors | smartphone | table",
+    "Manipulate colorful pieces :: buttons | table",
+    "Manipulate colorful pieces :: buttons",
+    "Adjust Mahjong tile :: mahjong tile | mahjong tile stack | table",
+    "Approach packing area :: cardboard box | items to pack | packing area",
+    "Interacting with colleagues :: person",
+    "Gathering items :: boxes | chairs | equipment | materials | people | supplies | tables | tools",
+    "Interacting with phone :: ceiling | chair | door | floor | person | smartphone | table | wall",
+    "Manipulate paper strip :: cardboard | craft materials | hands | marker | paper strip | ruler | scissors | table",
+    "Write on paper :: paper | pen | star beads",
+    "Manipulate paper strip :: chair | glue | marker | paper strip | person | ruler | scissors | table",
+    "Sort and arrange buttons :: buttons | table"
+  ],
+  "macro_f1": 0.0,
+  "metric_key": "action_object_relation_macro_f1",
+  "missing_pred_relation_count": 226,
+  "model_id": "cosmos3_super_reasoner",
+  "model_label": "Cosmos3-Super Reasoner",
+  "normalization_policy": "The action component uses the verified predicted action label when present. The object component is a canonical casefolded set because task 16 is an action plus object-set relation.",
+  "num_samples": 446,
+  "primary_metric": "action_object_relation_macro_f1",
+  "primary_score": 0.0,
+  "scope": "held_out_test_existing_verified_prediction_json",
+  "score_policy": "Derived from existing verified held-out prediction JSON. No new model inference was run; rows without a predicted action/object relation are counted as missing predictions.",
+  "scored_rows": 446,
+  "source_prediction_jsonl": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/predictions.jsonl",
+  "status": "pass",
+  "task_id": "action_object_relation",
+  "task_label": "Action-Object Relation",
+  "task_number": 16,
+  "title": "Cosmos3-Super Reasoner Action-Object Relation Probe",
+  "total_prediction_rows": 448,
+  "valid_pred_relation_count": 220,
+  "valid_pred_relation_rate": 0.49327354260089684
+}

results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/per_class_metrics.csv

@@ -0,0 +1,286 @@
+class_name,support,predicted,precision,recall,f1
+Adjust canned food on shelf :: canned food | cardboard box | store shelf,2,0,0.0,0.0,0.0
+Adjust item on shelf :: shelf | stationery package,2,0,0.0,0.0,0.0
+Adjust lantern shape :: red pleated paper lantern,2,0,0.0,0.0,0.0
+Adjust lantern string :: red paper lantern | string,2,0,0.0,0.0,0.0
+Adjust paper :: cardboard square | paper | pen | star beads,2,0,0.0,0.0,0.0
+Adjust pot position :: pot,2,0,0.0,0.0,0.0
+Adjust puzzle piece :: jigsaw puzzle | puzzle box | puzzle pieces,3,0,0.0,0.0,0.0
+Align canned food on shelf :: canned food | cardboard box | retail shelf,2,0,0.0,0.0,0.0
+Align edges of paper lantern :: hands | red paper lantern,2,0,0.0,0.0,0.0
+Align paper lantern edges :: hands | red paper lantern,2,0,0.0,0.0,0.0
+Apply adhesive tape to lantern :: adhesive tape | red paper lantern,2,0,0.0,0.0,0.0
+Approach boxes :: cardboard boxes | colleague | shelving unit,2,0,0.0,0.0,0.0
+Approaching and pressing the door switch :: glass door | switch | wall,4,0,0.0,0.0,0.0
+Approaching the table :: beads | chairs | table,2,0,0.0,0.0,0.0
+Arrange buttons :: red buttons | smartphone | table,4,0,0.0,0.0,0.0
+Arrange buttons in a line :: buttons | phone | table,4,0,0.0,0.0,0.0
+Arrange star beads :: paper | pen | power bank | smartphone | star beads,2,0,0.0,0.0,0.0
+Arrange star beads for counting :: paper | pen | star beads,2,0,0.0,0.0,0.0
+Attempt to fit puzzle piece :: puzzle board | puzzle piece,1,0,0.0,0.0,0.0
+Attempt to fit puzzle piece :: puzzle piece,2,0,0.0,0.0,0.0
+Bend and manipulate plastic strip :: plastic strip | stationary box | table | water bottle,4,0,0.0,0.0,0.0
+Browse smartphone screen :: paper strips | smartphone | star ornaments,3,0,0.0,0.0,0.0
+Bundle display hooks :: container | display hooks,2,0,0.0,0.0,0.0
+Closing the door :: door | dustpan,2,0,0.0,0.0,0.0
+Counting and organizing beads :: cardboard squares | paper | pen | star-shaped beads,2,0,0.0,0.0,0.0
+Counting star beads :: paper | pen | star beads,2,0,0.0,0.0,0.0
+Cut along the marked line :: cardboard | hand | utility knife,7,0,0.0,0.0,0.0
+Cut cardboard :: cardboard | desk | pen | ruler | utility knife,7,0,0.0,0.0,0.0
+Cut cardboard piece :: cardboard strip | scissors,3,0,0.0,0.0,0.0
+Entering the VR training room :: doorway | person | table,3,0,0.0,0.0,0.0
+Expand paper lantern :: adhesive tape roll | cardboard box | red paper lantern,2,0,0.0,0.0,0.0
+Extract wire hangers from box :: cardboard box | wire hangers,2,0,0.0,0.0,0.0
+Fold paper lantern :: red paper honeycomb lantern,2,0,0.0,0.0,0.0
+Fold plastic strip :: container with tools | purple plastic strip | water bottle | white table,3,0,0.0,0.0,0.0
+Gather star beads :: cardboard squares | mobile phone | paper | pen | power bank | star beads,2,0,0.0,0.0,0.0
+Gesturing :: cardboard pieces | marker | pencil case | ruler | scissors,2,0,0.0,0.0,0.0
+Grasp cleaning bottle :: bowls | chopping board | cleaning fluid bottle,2,0,0.0,0.0,0.0
+Grasp lantern :: red paper honeycomb lantern,2,0,0.0,0.0,0.0
+Grasp lantern component :: cardboard box | paper lantern | tape,2,0,0.0,0.0,0.0
+Grasping cleaning cloth :: cleaning cloth | countertop,2,0,0.0,0.0,0.0
+Greeting/acknowledging participants :: person | table | vr headset,3,0,0.0,0.0,0.0
+Handle paper lantern component :: cardboard box | paper lantern component | plastic bag | red paper lantern,2,0,0.0,0.0,0.0
+Hold and bend plastic strip :: bottle | purple plastic strip | stationery box,3,0,0.0,0.0,0.0
+Hold and manipulate paper strip :: beads | mobile phone | power bank | yellow paper strip,2,0,0.0,0.0,0.0
+Hold beads :: paper | pen | power bank | smartphone | star-shaped beads,2,0,0.0,0.0,0.0
+Hold canned food :: box of cans | can of soup | shelf,2,0,0.0,0.0,0.0
+Hold cardboard piece :: cardboard pieces | marker | pencil case | ruler | scissors,3,0,0.0,0.0,0.0
+Hold container lid :: dustpan | red plastic container lid,2,0,0.0,0.0,0.0
+Hold paper lantern :: red paper lantern | sofa,2,0,0.0,0.0,0.0
+Hold smartphone :: kettle | kitchen counter | sink | smartphone,1,0,0.0,0.0,0.0
+Hold smartphone :: quilling paper strips | small blue beads | smartphone,3,0,0.0,0.0,0.0
+Identify next cardboard piece :: cardboard pieces | marker,3,0,0.0,0.0,0.0
+Inspect shelf condition :: colleague | shelf,2,0,0.0,0.0,0.0
+Interact with smartphone :: beads | smartphone | yellow paper strip,2,0,0.0,0.0,0.0
+Interact with smartphone :: cans | shelf | smartphone,2,0,0.0,0.0,0.0
+Lift pot lid :: pot | pot lid,1,0,0.0,0.0,0.0
+Manipulate adhesive strip :: adhesive strip | paper sheets | puzzle box | smartphone | water bottle,5,0,0.0,0.0,0.0
+Manipulate bead :: bead piles | container | paper strips | yellow bead,2,0,0.0,0.0,0.0
+Manipulate beads :: blue beads | power bank | smartphone | yellow beads,2,0,0.0,0.0,0.0
+Manipulate craft paper strips :: paper strips | scissors | smartphone,4,0,0.0,0.0,0.0
+Manipulate craft piece :: craft pieces | scissors | smartphone,4,0,0.0,0.0,0.0
+Manipulate material :: blue crafting material | hand,2,0,0.0,0.0,0.0
+Manipulate paper decoration :: paper cone | paper decoration | smartphone | water bottle,5,0,0.0,0.0,0.0
+Manipulate paper edge :: hands | paper cone | puzzle box | smartphone | water bottle,5,0,0.0,0.0,0.0
+Manipulate paper strip :: container with tools | table | yellow paper strip,2,0,0.0,0.0,0.0
+Manipulate paper strip :: craft materials | purple paper strip | scissors | smartphone,4,0,0.0,0.0,0.0
+Manipulate paper strip :: paper cone | paper strip | puzzle box | smartphone | water bottle,5,0,0.0,0.0,0.0
+Manipulate paper strip :: purple paper strip | quilling paper pile | smartphone,3,0,0.0,0.0,0.0
+Manipulate plastic strip :: purple plastic strip | storage bin | water bottle,3,0,0.0,0.0,0.0
+Manipulate plastic strips :: desk | plastic strips | water bottle,3,0,0.0,0.0,0.0
+Manipulate puzzle piece :: jigsaw puzzle | puzzle piece,3,0,0.0,0.0,0.0
+Manipulate puzzle pieces :: puzzle box | puzzle mat | puzzle pieces,3,0,0.0,0.0,0.0
+Manipulate yellow strip :: beads | cell phone | pen | yellow strip,2,0,0.0,0.0,0.0
+Manipulating paper strips :: beads | blue paper strip | yellow paper strip,2,0,0.0,0.0,0.0
+Mark cardboard piece :: cardboard piece | marker,1,0,0.0,0.0,0.0
+Mark cardboard piece :: cardboard piece | marker | pouch,2,0,0.0,0.0,0.0
+Marking cardboard piece :: cardboard pieces | marker | ruler | scissors,3,0,0.0,0.0,0.0
+Move dustpan to side :: dustpan,1,0,0.0,0.0,0.0
+Move hand away :: canned food | retail shelf,2,0,0.0,0.0,0.0
+Move hand away from shelf :: canned food | cardboard box | store shelf,2,0,0.0,0.0,0.0
+Move marker and adjust hand :: cardboard pieces | marker,3,0,0.0,0.0,0.0
+Move phone :: cardboard | smartphone | utility knife,7,0,0.0,0.0,0.0
+Move pot :: faucet | pot | sink,1,0,0.0,0.0,0.0
+Move smartphone :: craft beads | paper strips | smartphone,3,0,0.0,0.0,0.0
+Move through aisle :: aisle floor | display hooks | metal shelving units,2,0,0.0,0.0,0.0
+Move through the training room :: chairs | fire extinguisher | tables | vr headsets,3,0,0.0,0.0,0.0
+Move to shelf :: cardboard box | colleague | shelves,2,0,0.0,0.0,0.0
+Move towards kitchen area :: cloth | sink,1,0,0.0,0.0,0.0
+Move towards the stove :: blue bowl | faucet | metal container | red bowl | sink,1,0,0.0,0.0,0.0
+Observe and pause :: cardboard pieces | marker | pencil case | ruler | scissors,2,0,0.0,0.0,0.0
+Observe and walk through store :: colleague | inventory boxes | shelves,2,0,0.0,0.0,0.0
+Observe colleague and workspace :: price tag | shelves | watch,2,0,0.0,0.0,0.0
+Observe puzzle progress :: hand | jigsaw puzzle,3,0,0.0,0.0,0.0
+Observe workspace :: cardboard boxes | colleague | shelving unit,2,0,0.0,0.0,0.0
+Open earbud case :: earbud case,2,0,0.0,0.0,0.0
+Open folded paper lantern :: cardboard box | red pleated paper lantern,2,0,0.0,0.0,0.0
+Open paper lantern :: red paper honeycomb lantern,2,0,0.0,0.0,0.0
+Open paper lantern component :: paper lantern component,2,0,0.0,0.0,0.0
+Open stove pot lid :: blue bowl | cloth | faucet | red bowl | sink | soap dispenser | white bowl,1,0,0.0,0.0,0.0
+Operate smartphone :: craft paper strips | folded paper fan | smartphone,4,0,0.0,0.0,0.0
+Organize cardboard pieces :: cardboard pieces | marker | pencil case | ruler | scissors,2,0,0.0,0.0,0.0
+Pick up button :: buttons | table,3,0,0.0,0.0,0.0
+Pick up can :: canned food | cardboard box,2,0,0.0,0.0,0.0
+Pick up canned food :: canned food | cardboard box,2,0,0.0,0.0,0.0
+Pick up dustpan :: dustpan | smartphone,1,0,0.0,0.0,0.0
+Pick up items from the shopping bag :: cardboard boxes | red shopping bag | retail shelf,2,0,0.0,0.0,0.0
+Pick up new cardboard piece :: cardboard piece | marker,2,0,0.0,0.0,0.0
+Pick up packaged paper lantern component :: cardboard box | packaged paper lantern component,1,0,0.0,0.0,0.0
+Pick up pen :: paper | pen | star beads,2,0,0.0,0.0,0.0
+Pick up puzzle piece :: jigsaw puzzle | puzzle piece,3,0,0.0,0.0,0.0
+Pick up small piece of material :: blue crafting material | hand,2,0,0.0,0.0,0.0
+Pick up smartphone :: cans | shelf | smartphone,2,0,0.0,0.0,0.0
+Pick up star bead :: cardboard squares | mobile phone | paper | pen | power bank | star beads,2,0,0.0,0.0,0.0
+Pick up utility knife :: cardboard | utility knife,6,0,0.0,0.0,0.0
+Picking up bottle :: bottle,1,0,0.0,0.0,0.0
+Picking up crafting material :: beads | papers | pen | table,2,0,0.0,0.0,0.0
+Place and count bead :: paper | pen | star beads,2,0,0.0,0.0,0.0
+Place another canned food on shelf :: box | canned food,2,0,0.0,0.0,0.0
+Place button :: buttons | hand | smartphone | table,1,0,0.0,0.0,0.0
+Place button :: buttons | hand | table,2,0,0.0,0.0,0.0
+Place can on shelf :: canned food | retail shelf,2,0,0.0,0.0,0.0
+Place canned food on shelf :: can of vegetables | cardboard boxes | store shelf,1,0,0.0,0.0,0.0
+Place cloth on floor :: cloth,1,0,0.0,0.0,0.0
+Place hand on table :: craft beads | paper strips | smartphone,3,0,0.0,0.0,0.0
+Place item on shelf :: stationery package,2,0,0.0,0.0,0.0
+Place items on the shelf :: packaged items | retail shelf,2,0,0.0,0.0,0.0
+Place lid back :: pot | pot lid,1,0,0.0,0.0,0.0
+Place marked piece down :: cardboard piece | marker,2,0,0.0,0.0,0.0
+Place material :: bead design | blue crafting material | hand,2,0,0.0,0.0,0.0
+Place phone down :: beads | pencil holder | smartphone | yellow paper strip,2,0,0.0,0.0,0.0
+Place piece into puzzle :: jigsaw puzzle | puzzle piece,3,0,0.0,0.0,0.0
+Place puzzle piece :: puzzle board | puzzle piece,3,0,0.0,0.0,0.0
+Place smartphone down :: power bank | quilling paper strips | small paper stars | smartphone,1,0,0.0,0.0,0.0
+Place smartphone down :: quilling paper strips | small paper stars | smartphone,2,0,0.0,0.0,0.0
+Place smartphone on stand :: saucepan | smartphone | smartphone stand | yellow jacket,1,0,0.0,0.0,0.0
+Place towel :: pot | towel,1,0,0.0,0.0,0.0
+Placing paper strip :: adhesive strip | paper cone | phone,2,0,0.0,0.0,0.0
+Placing paper strip :: paper cone | phone | puzzle box | water bottle,2,0,0.0,0.0,0.0
+Preparing to craft :: beads | chairs | table,2,0,0.0,0.0,0.0
+Put down smartphone :: paper stars | paper strips | smartphone,2,0,0.0,0.0,0.0
+Put down smartphone :: power bank | smartphone,1,0,0.0,0.0,0.0
+Reach for another item :: item | shelf,1,0,0.0,0.0,0.0
+Reach for cleaning supplies :: bowls | chopping board | cleaning fluid bottle,1,0,0.0,0.0,0.0
+Reach for craft items :: smartphone | star-shaped craft items | table,3,0,0.0,0.0,0.0
+Reach for next can :: can of vegetables | cardboard boxes | store shelf,1,0,0.0,0.0,0.0
+Reach for next canned food :: box | canned food | retail shelf,1,0,0.0,0.0,0.0
+Reach for next item :: packaged item | shelf,1,0,0.0,0.0,0.0
+Reach for puzzle piece :: puzzle board | puzzle box | puzzle pieces,2,0,0.0,0.0,0.0
+Reach for wire hangers :: cardboard box | wire hangers,1,0,0.0,0.0,0.0
+Reach into box :: box of cans,1,0,0.0,0.0,0.0
+Record count :: paper | pen | star-shaped beads,2,0,0.0,0.0,0.0
+Release cardboard piece and gesture :: cardboard piece | cardboard piles | marker | pouch | ruler | scissors,2,0,0.0,0.0,0.0
+Release hook :: display hook,1,0,0.0,0.0,0.0
+Release lantern :: red paper lantern,1,0,0.0,0.0,0.0
+Release paper strip :: craft beads | paper strip | scissors | smartphone,4,0,0.0,0.0,0.0
+Release puzzle piece :: jigsaw puzzle | puzzle box | puzzle pieces,2,0,0.0,0.0,0.0
+Release scissors :: craft paper strips | folded paper fan | scissors | smartphone,3,0,0.0,0.0,0.0
+Release smartphone :: paper scraps | scissors | smartphone | table,3,0,0.0,0.0,0.0
+Remove cleaning bottle :: cleaning bottle | plastic bowls,1,0,0.0,0.0,0.0
+Remove paper lantern part from packaging :: paper lantern | red hand fan,1,0,0.0,0.0,0.0
+Remove plastic packaging :: packaging | paper lantern component,1,0,0.0,0.0,0.0
+Reposition hand :: cardboard | utility knife,3,0,0.0,0.0,0.0
+Resume observation :: cardboard pieces | marker | pencil case | ruler | scissors,2,0,0.0,0.0,0.0
+Retrieve canned food from box :: box | canned food,1,0,0.0,0.0,0.0
+Retrieve next canned food item :: canned food | cardboard box,1,0,0.0,0.0,0.0
+Retrieving more beads :: paper | pen | star beads,2,0,0.0,0.0,0.0
+Rinse cloth in sink :: cloth | sink | water faucet,1,0,0.0,0.0,0.0
+Scroll smartphone screen :: paper stars | paper strips | smartphone,3,0,0.0,0.0,0.0
+Search for puzzle piece :: jigsaw puzzle | puzzle pieces,2,0,0.0,0.0,0.0
+Secure paper edges with adhesive :: adhesive strip | paper cone pieces | puzzle box | smartphone | water bottle,4,0,0.0,0.0,0.0
+Securing paper structure :: decorative stars | paper strips | smartphone | water bottle,4,0,0.0,0.0,0.0
+Sort and adjust button line :: buttons | smartphone | table,3,0,0.0,0.0,0.0
+Sort and arrange buttons :: buttons | smartphones | soda can | table,3,0,0.0,0.0,0.0
+Sort and count beads :: paper | pen | star beads,2,0,0.0,0.0,0.0
+Sort and place buttons :: buttons | coca-cola can | smartphone,3,0,0.0,0.0,0.0
+Sort beads :: paper | pen | smartphone | star-shaped beads,2,0,0.0,0.0,0.0
+Sort beads and write count :: paper | pen | power bank | smartphone | star-shaped beads,1,0,0.0,0.0,0.0
+Sort button :: buttons | cell phone,3,0,0.0,0.0,0.0
+Sort buttons :: buttons | table,3,0,0.0,0.0,0.0
+Sort craft items :: star-shaped craft items | table,3,0,0.0,0.0,0.0
+Sort puzzle pieces :: jigsaw puzzle pieces | table,2,0,0.0,0.0,0.0
+Sort small craft pieces :: paper strips | scissors | smartphone | star-shaped craft pieces,3,0,0.0,0.0,0.0
+Sort star-shaped beads :: marker | mobile phone | paper | power bank | star-shaped beads,1,0,0.0,0.0,0.0
+Start cutting :: cardboard | utility knife,2,0,0.0,0.0,0.0
+Stir contents :: cooking utensil | pot,1,0,0.0,0.0,0.0
+Use phone :: beads | paper | power bank | smartphone,2,0,0.0,0.0,0.0
+Use phone while crafting :: beads | pencil holder | smartphone | yellow paper strip,1,0,0.0,0.0,0.0
+Use smartphone :: buttons | chair | smartphone | table,2,0,0.0,0.0,0.0
+Use smartphone :: buttons | smartphone | table,1,0,0.0,0.0,0.0
+Use smartphone :: charging cable | paper strips | power bank | smartphone | star-shaped paper crafts,2,0,0.0,0.0,0.0
+Use smartphone :: containers | kettle | kitchen counter | rice cooker | smartphone,1,0,0.0,0.0,0.0
+Walk towards other aisles :: retail store aisle,1,0,0.0,0.0,0.0
+Walk towards shelves :: cardboard boxes | red bin | shelving unit,1,0,0.0,0.0,0.0
+Walking across the room :: chair | fire extinguisher | office | table,1,0,0.0,0.0,0.0
+Walking in the hallway :: hallway | people | tables | vr headsets,3,0,0.0,0.0,0.0
+Walking towards door :: door | dustpan,1,0,0.0,0.0,0.0
+Washing hands in sink :: faucet | sink,1,0,0.0,0.0,0.0
+Wipe kitchen counter :: door | laundry basket | mop,1,0,0.0,0.0,0.0
+Wiping countertop :: cleaning cloth | countertop,1,0,0.0,0.0,0.0
+Write count on paper :: marker | mobile phone | paper | power bank | star-shaped beads,1,0,0.0,0.0,0.0
+Write on paper :: cardboard square | paper | pen | star beads,1,0,0.0,0.0,0.0
+sort craft materials :: paper pieces | scissors | smartphone,3,0,0.0,0.0,0.0
+Pick up and place canned goods on shelf :: bin | canned goods | shelf,0,4,0.0,0.0,0.0
+Browsing smartphone content :: smartphone,0,60,0.0,0.0,0.0
+Place item on shelf :: retail item | shelf,0,8,0.0,0.0,0.0
+Place item on shelf :: canned food | shelf,0,7,0.0,0.0,0.0
+<missing_pred_relation>,0,226,0.0,0.0,0.0
+Approach packing area :: items to pack | packing area,0,11,0.0,0.0,0.0
+Approach restocking supplies :: aisle | restocking supplies | shelf,0,1,0.0,0.0,0.0
+unknown :: unknown,0,7,0.0,0.0,0.0
+Approach table :: materials | table | tools | work surface,0,1,0.0,0.0,0.0
+Place item in container :: canned goods | plastic container | shopping bag,0,2,0.0,0.0,0.0
+Pick up canned food :: canned food | shelf,0,2,0.0,0.0,0.0
+Adjusting items on the shelf :: items | shelf,0,1,0.0,0.0,0.0
+Wipe hands :: hands | sink | water bottle,0,1,0.0,0.0,0.0
+Approach the stove :: cooking pot | kitchen counter | stove,0,1,0.0,0.0,0.0
+Place item on shelf :: plush toy | shelf,0,1,0.0,0.0,0.0
+Place item on shelf :: canned goods | shelf,0,1,0.0,0.0,0.0
+Adjust cardboard :: cardboard pieces | workspace surface,0,1,0.0,0.0,0.0
+Adjust cardboard :: cardboard | cutting mat | glue stick | marker | measuring tape | ruler | scissors | work table,0,1,0.0,0.0,0.0
+Approach packing area :: cardboard pieces | marker | ruler | scissors | work table,0,1,0.0,0.0,0.0
+Adjust cardboard :: cardboard piece | marker | ruler | workspace surface,0,2,0.0,0.0,0.0
+Adjust cardboard position :: cardboard piece | marker | ruler | scissors | work surface,0,1,0.0,0.0,0.0
+Adjust cardboard position :: cardboard piece | hands | work surface,0,1,0.0,0.0,0.0
+Adjust cardboard :: cardboard piece | glue stick | marker | measuring tape | pencil | ruler | scissors | work table,0,1,0.0,0.0,0.0
+Adjust cardboard :: cardboard | glue stick | marker | measuring tape | pencil | ruler | scissors | work table,0,1,0.0,0.0,0.0
+Adjust cardboard position :: cardboard piece | scissors | work table,0,1,0.0,0.0,0.0
+Adjust cardboard position :: cardboard piece | scissors | work surface,0,2,0.0,0.0,0.0
+Cut cardboard with utility knife :: cardboard | ruler | table | utility knife,0,3,0.0,0.0,0.0
+Cut cardboard :: cardboard | glue | marker | measuring tape | pen | ruler | scissors | work surface,0,1,0.0,0.0,0.0
+Adjusting items on shelf :: containers | retail items | shelf,0,2,0.0,0.0,0.0
+Approach packing area :: container | items to pack | packing area,0,1,0.0,0.0,0.0
+Adjust cardboard divider :: cardboard divider | retail items | shelf,0,1,0.0,0.0,0.0
+Adjusting items on shelf :: retail items | shelf,0,3,0.0,0.0,0.0
+Approach packing area :: boxes | items to pack | packing area,0,2,0.0,0.0,0.0
+Adjust grip :: canned food | plastic container | shelf,0,2,0.0,0.0,0.0
+Adjust item on shelf :: retail items | shelf,0,1,0.0,0.0,0.0
+Approach packing area :: cardboard pieces | packing area | storage bins,0,1,0.0,0.0,0.0
+Adjust cardboard position :: cardboard pieces | scissors | table surface,0,1,0.0,0.0,0.0
+Adjust cardboard divider :: cardboard divider | cardboard pieces | table surface,0,1,0.0,0.0,0.0
+Adjust cardboard divider :: cardboard divider | cardboard pieces | scissors | table,0,1,0.0,0.0,0.0
+Place canned food on shelf :: canned food | shelf,0,9,0.0,0.0,0.0
+Pick up canned food :: bin | canned food | shelf,0,1,0.0,0.0,0.0
+Pick up canned food :: box | canned food | shelf,0,1,0.0,0.0,0.0
+Pick up canned food :: canned food | container | shelf,0,1,0.0,0.0,0.0
+Adjust canned food on shelf :: canned food | shelf,0,1,0.0,0.0,0.0
+Move along the shelf :: retail items | shelf,0,1,0.0,0.0,0.0
+Picking up and placing canned goods :: canned goods | shelf,0,1,0.0,0.0,0.0
+Move along the shelf :: canned goods | plastic container | shelf,0,1,0.0,0.0,0.0
+Adjust item on shelf :: retail item | shelf,0,1,0.0,0.0,0.0
+Browsing smartphone content :: retail items | shelf | smartphone,0,1,0.0,0.0,0.0
+Manipulate paper strip :: paper strip | scissors | table,0,7,0.0,0.0,0.0
+Manipulate paper strip :: marker | paper strip | pink cloth | ruler | scissors | smartphone | table | water bottle,0,1,0.0,0.0,0.0
+Adjust grip :: hand | red container,0,1,0.0,0.0,0.0
+Approach packing area :: boxes | packaging materials | red hat | table,0,1,0.0,0.0,0.0
+Approach packing area :: boxes | packaging materials | red cap | table,0,1,0.0,0.0,0.0
+Manipulate paper strip :: paper strip,0,3,0.0,0.0,0.0
+Adjust lantern string :: handle | lantern | string,0,1,0.0,0.0,0.0
+Adjust grip :: lid | red container,0,1,0.0,0.0,0.0
+Approach packing area :: items to pack | packing area | packing materials,0,1,0.0,0.0,0.0
+Adjust lantern string :: lantern handle | lantern string | paper lantern,0,2,0.0,0.0,0.0
+Adjust grip :: red container | small white object,0,1,0.0,0.0,0.0
+Adjust lantern string :: handle component | paper lantern | string,0,1,0.0,0.0,0.0
+Approach table :: people | table,0,1,0.0,0.0,0.0
+Approach table :: items on table | people | table,0,1,0.0,0.0,0.0
+Adjust Mahjong tile :: mahjong tile | mahjong tile stack | table surface,0,2,0.0,0.0,0.0
+Adjusting and placing down paper pieces :: hand | paper pieces | table,0,1,0.0,0.0,0.0
+Approach table :: cardboard | chair | mahjong tiles | marker | paper | ruler | scissors | table,0,2,0.0,0.0,0.0
+Approach table :: beads | cardboard | marker | paper | pen | ruler | scissors | table,0,1,0.0,0.0,0.0
+Manipulate paper strip :: craft materials | hands | marker | paper strip | ruler | scissors | table | workspace,0,5,0.0,0.0,0.0
+Manipulate paper strip :: craft materials | glue | hands | marker | paper strip | ruler | scissors | table,0,2,0.0,0.0,0.0
+Adjust bead piles :: beads | table,0,3,0.0,0.0,0.0
+Manipulate paper strip :: beads | glue | marker | paper strip | ruler | scissors | smartphone | table,0,1,0.0,0.0,0.0
+Manipulate paper strip :: beads | mahjong tiles | marker | paper strip | ruler | scissors | smartphone | table,0,1,0.0,0.0,0.0
+Manipulate colorful pieces :: buttons | table,0,4,0.0,0.0,0.0
+Manipulate colorful pieces :: buttons,0,1,0.0,0.0,0.0
+Adjust Mahjong tile :: mahjong tile | mahjong tile stack | table,0,1,0.0,0.0,0.0
+Approach packing area :: cardboard box | items to pack | packing area,0,1,0.0,0.0,0.0
+Interacting with colleagues :: person,0,2,0.0,0.0,0.0
+Gathering items :: boxes | chairs | equipment | materials | people | supplies | tables | tools,0,1,0.0,0.0,0.0
+Interacting with phone :: ceiling | chair | door | floor | person | smartphone | table | wall,0,2,0.0,0.0,0.0
+Manipulate paper strip :: cardboard | craft materials | hands | marker | paper strip | ruler | scissors | table,0,1,0.0,0.0,0.0
+Write on paper :: paper | pen | star beads,0,4,0.0,0.0,0.0
+Manipulate paper strip :: chair | glue | marker | paper strip | person | ruler | scissors | table,0,1,0.0,0.0,0.0
+Sort and arrange buttons :: buttons | table,0,3,0.0,0.0,0.0

results/omni_finetune/model_output_task_probes_20260616/summary.json

@@ -0,0 +1,36 @@
+{
+  "generated_at_utc": "2026-06-16T13:35:37+00:00",
+  "methods": {
+    "cosmos3_nano_future_window": {
+      "label": "Cosmos3-Nano Future Window",
+      "reason": "verified future-window predictions do not contain object-set fields",
+      "source_prediction_jsonl": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/future_predictions.jsonl",
+      "status": "unsupported_without_required_fields"
+    },
+    "cosmos3_super_reasoner": {
+      "action_object_relation_accuracy": 0.0,
+      "action_object_relation_macro_f1": 0.0,
+      "label": "Cosmos3-Super Reasoner",
+      "scored_rows": 446,
+      "source_metrics_json": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json",
+      "source_prediction_jsonl": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/predictions.jsonl",
+      "status": "scored",
+      "valid_pred_relation_rate": 0.49327354260089684
+    },
+    "qwen3_omni_v6_lora": {
+      "action_object_relation_accuracy": 0.000996512207274539,
+      "action_object_relation_macro_f1": 0.0002220083079671497,
+      "label": "Qwen3-Omni v6 LoRA",
+      "scored_rows": 4014,
+      "source_metrics_json": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json",
+      "source_prediction_jsonl": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/predictions.jsonl",
+      "status": "scored",
+      "valid_pred_relation_rate": 0.9990034877927254
+    }
+  },
+  "scope": "Task-specific scoring from existing verified held-out model outputs. No new model inference, training, or target backfilling is performed.",
+  "scored_method_task_count_added": 2,
+  "status": "pass",
+  "task_count_added_to_matrix": 1,
+  "title": "Existing Model-Output Task Probes"
+}