Add files using upload-large-folder tool

FIGURE_INDEX.md

@@ -34,9 +34,9 @@ Public figures, diagrams, charts, and derived modality thumbnails. Raw Xperience
 | Research direction coverage chart | `docs/assets/charts/research_direction_coverage.svg` | 1180 x 700 | `scripts/generate_visualizations.py` | Four-track coverage map for Ropedia research directions. |
 | Research direction extension chart | `docs/assets/charts/research_direction_extension_tasks.svg` | 1420 x 920 | `scripts/generate_visualizations.py` | Four coded extension probes, one per Ropedia research direction. |
 | Unified 20-task provenance chart | `docs/assets/charts/tier2_task_suite.svg` | 1440 x 832 | `scripts/tier2_task_suite.py` | Historical provenance rows inside the unified 20-task suite with aligned minimal and neural baseline metrics. |
-| Unified 20-task model radar | `docs/assets/charts/unified_task_model_radar.svg` | 2400 x 1840 | `scripts/build_unified_task_model_radar.py` | Twenty-axis direction-aware comparison of minimal and neural MLP baselines, with 128-episode metadata, Qwen3, and Cosmos task-aligned overlay points and branch notes. |
-| Single-episode 20-task model radar | `docs/assets/charts/single_episode_task_model_radar.svg` | 2400 x 1840 | `scripts/build_unified_task_model_radar.py` | Twenty-axis split radar for the one public-sample episode, comparing Minimal and Neural MLP as two complete 20/20 scored polygons. |
-| 128-episode 20-task model radar | `docs/assets/charts/episode128_task_model_radar.svg` | 2400 x 1840 | `scripts/build_unified_task_model_radar.py` | Twenty-axis split radar for selected 128-episode methods: raw-feature simple/NN as complete scored polygons plus metadata, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano task-aligned overlays. |
+| Unified 20-task model radar | `docs/assets/charts/unified_task_model_radar.svg` | 2400 x 1900 | `scripts/build_unified_task_model_radar.py` | Grouped small-multiple 20-task radar board for all nine methods, separating single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows while preserving task keys and proxy notes. |
+| Single-episode 20-task model radar | `docs/assets/charts/single_episode_task_model_radar.svg` | 2400 x 1900 | `scripts/build_unified_task_model_radar.py` | Twenty-axis split radar for the one public-sample episode, comparing Minimal and Neural MLP as two complete 20/20 scored polygons. |
+| 128-episode 20-task model radar | `docs/assets/charts/episode128_task_model_radar.svg` | 2400 x 1900 | `scripts/build_unified_task_model_radar.py` | Grouped 20-task radar for selected 128-episode methods: metadata/text baselines, raw-feature simple/NN, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano with local legends and proxy notes. |
 | Feature block chart | `docs/assets/charts/feature_blocks.svg` | 1100 x 760 | `scripts/generate_visualizations.py` | Feature allocation by modality block. |
 | Minimal task score chart | `docs/assets/charts/episode_task_scores.svg` | 1100 x 556 | `scripts/generate_visualizations.py` | Minimal baseline metric snapshot across the task suite. |
 | Cross-modal retrieval chart | `docs/assets/charts/cross_modal_retrieval.svg` | 1100 x 284 | `scripts/generate_visualizations.py` | Retrieval behavior chart for the cross-modal task. |

PROJECT_README.md

@@ -788,22 +788,21 @@ suite.
 
 ![Unified 20-task model radar](docs/assets/charts/unified_task_model_radar.svg)
 
-The unified radar compares all 20 task axes with two filled colors for the
-minimal and neural MLP baselines. Every method now has 20 explicit result
-records in the public matrix; numeric points appear only where the runner or
-verified package produced that task target. The 128-episode raw-feature
-simple/NN overlays are plotted on all 20 axes backed by the exported
-4430-dimensional sensor NPZ blocks. Tasks 15 and 19 are marked as compact-proxy
-completions because the 128 export lacks raw interaction strings and paired
-video-view embeddings. The verified model-output probe package adds task-16
-action/object relation scores for Qwen3-Omni and Cosmos3-Super, plus a task-13
-long-horizon next-action score for Cosmos3-Nano derived from its existing
-held-out future-window predictions. Metadata-only baselines and model diagnostics
-now have scored records on all 20 axes; six compact-proxy scores stay
-explicitly marked instead of being blended into direct-target metrics.
+The unified radar is now a grouped small-multiple comparison board instead of a
+nine-method overlay. It keeps all 20 task axes and all 9 method rows visible,
+but separates the methods into single-episode, 128-episode metadata/text,
+128-episode raw-feature, and foundation-model panels. Every method has 20
+explicit result records in the public matrix. Tasks 15 and 19 are marked as
+compact-proxy completions where the 128 export lacks raw interaction strings or
+paired video-view embeddings; those six proxy cells stay explicitly marked
+instead of being blended into direct-target metrics. The SVG uses
+`sqrt(normalized_score)` only for visual radius so small but real differences
+are readable; raw metrics and exact linear normalized scores remain in JSON and
+the table.
 Cosmos3-Super forward-dynamics LoRA
-remains a separate artifact card because its camera-pose proxy MSE is not one of the 20
-task metrics. The machine-readable copies are
+remains a separate artifact card because its camera-pose proxy MSE is not one of
+the 20 task metrics.
+The machine-readable copies are
 [`docs/data/unified_task_model_radar.json`](docs/data/unified_task_model_radar.json)
 and
 [`docs/data/task_method_20_result_matrix.json`](docs/data/task_method_20_result_matrix.json);
@@ -822,13 +821,13 @@ For easier reading, the same source data is also split into two focused radars:
 
 ![128-episode 20-task model radar](docs/assets/charts/episode128_task_model_radar.svg)
 
-The single-episode radar isolates Minimal vs Neural MLP, both with 20/20 scored
-public-sample axes. The 128-episode radar isolates metadata/raw baselines,
-Qwen3-Omni v6 LoRA, Cosmos3-Super Reasoner, and Cosmos3-Nano Future Window:
-metadata and raw-feature simple/NN baselines are now complete 20/20
-multi-episode records, with documented compact proxy notes where the public
-export lacks the original raw target. The current matrix has 180/180 scored
-method-task records.
+The single-episode radar uses one enlarged panel for Minimal vs Neural MLP, both
+with 20/20 scored public-sample axes. The 128-episode radar uses three grouped
+panels for metadata/text baselines, raw-feature baselines, and foundation-model
+rows: metadata and raw-feature simple/NN baselines are now complete 20/20
+multi-episode records, and Qwen3-Omni v6 LoRA, Cosmos3-Super Reasoner, and
+Cosmos3-Nano Future Window each carry 20 scored task records. The current matrix
+has 180/180 scored method-task records.
 
 The website raw sample browser includes a concise stream-to-feature ledger
 backed by [`docs/data/modality_atlas.json`](docs/data/modality_atlas.json) and
@@ -865,7 +864,7 @@ scripts/
   research_direction_extension_tasks.py # one extra data-backed probe per track
   tier2_task_suite.py              # historical-name provenance builder for unified task rows
   build_unified_task_suite.py       # builds TASK_SUITE_20.md and task_suite_20.json
-  build_unified_task_model_radar.py # builds the unified 20-axis model comparison chart
+  build_unified_task_model_radar.py # builds grouped 20-axis model comparison radars
   build_task_method_20_gap_audit.py # builds the explicit 180/180 scored-cell ledger
   task_walkthroughs.py              # human-readable task-card and walkthrough-storyboard metadata
   generate_visualizations.py        # refreshes SVG charts + summary JSON
@@ -908,9 +907,9 @@ docs/
   data/additional_development_directions.json # concrete non-backbone project directions
   data/summary_metrics.json         # website-readable metrics bundle
   data/task_suite_20.json           # unified 20-task suite bundle
-  data/unified_task_model_radar.json # 20-task radar values and method overlays
-  data/single_episode_task_model_radar.json # 1-episode split radar values
-  data/episode128_task_model_radar.json # 128-episode split radar values
+  data/unified_task_model_radar.json # 20-task radar values, groups, and sources
+  data/single_episode_task_model_radar.json # 1-episode grouped radar values
+  data/episode128_task_model_radar.json # 128-episode grouped radar values
   data/task_method_20_result_matrix.json # 9-method x 20-task result matrix
   data/task_method_20_gap_audit.json # explicit 180/180 scored-cell ledger
   data/evidence_contract.json       # machine-readable project scope
@@ -933,9 +932,9 @@ docs/
   assets/pipeline_diagram.png       # verified episode pipeline graphic
   assets/qwen3_omni_lora_pipeline.png # Qwen3-Omni LoRA training-flow figure
   assets/task_architectures.png     # verified task-head architecture map
-  assets/charts/unified_task_model_radar.svg # 20-task minimal/NN/Qwen3-Omni/Cosmos3 radar
-  assets/charts/single_episode_task_model_radar.svg # 1-episode split radar
-  assets/charts/episode128_task_model_radar.svg # 128-episode split radar
+  assets/charts/unified_task_model_radar.svg # 9-method grouped small-multiple radar board
+  assets/charts/single_episode_task_model_radar.svg # 1-episode enlarged radar panel
+  assets/charts/episode128_task_model_radar.svg # 128-episode grouped radar panels
   assets/charts/*.svg               # regenerated visualizations
 
 notes/

README.md

@@ -810,22 +810,21 @@ suite.
 
 ![Unified 20-task model radar](docs/assets/charts/unified_task_model_radar.svg)
 
-The unified radar compares all 20 task axes with two filled colors for the
-minimal and neural MLP baselines. Every method now has 20 explicit result
-records in the public matrix; numeric points appear only where the runner or
-verified package produced that task target. The 128-episode raw-feature
-simple/NN overlays are plotted on all 20 axes backed by the exported
-4430-dimensional sensor NPZ blocks. Tasks 15 and 19 are marked as compact-proxy
-completions because the 128 export lacks raw interaction strings and paired
-video-view embeddings. The verified model-output probe package adds task-16
-action/object relation scores for Qwen3-Omni and Cosmos3-Super, plus a task-13
-long-horizon next-action score for Cosmos3-Nano derived from its existing
-held-out future-window predictions. Metadata-only baselines and model diagnostics
-now have scored records on all 20 axes; six compact-proxy scores stay
-explicitly marked instead of being blended into direct-target metrics.
+The unified radar is now a grouped small-multiple comparison board instead of a
+nine-method overlay. It keeps all 20 task axes and all 9 method rows visible,
+but separates the methods into single-episode, 128-episode metadata/text,
+128-episode raw-feature, and foundation-model panels. Every method has 20
+explicit result records in the public matrix. Tasks 15 and 19 are marked as
+compact-proxy completions where the 128 export lacks raw interaction strings or
+paired video-view embeddings; those six proxy cells stay explicitly marked
+instead of being blended into direct-target metrics. The SVG uses
+`sqrt(normalized_score)` only for visual radius so small but real differences
+are readable; raw metrics and exact linear normalized scores remain in JSON and
+the table.
 Cosmos3-Super forward-dynamics LoRA
-remains a separate artifact card because its camera-pose proxy MSE is not one of the 20
-task metrics. The machine-readable copies are
+remains a separate artifact card because its camera-pose proxy MSE is not one of
+the 20 task metrics.
+The machine-readable copies are
 [`docs/data/unified_task_model_radar.json`](docs/data/unified_task_model_radar.json)
 and
 [`docs/data/task_method_20_result_matrix.json`](docs/data/task_method_20_result_matrix.json);
@@ -844,13 +843,13 @@ For easier reading, the same source data is also split into two focused radars:
 
 ![128-episode 20-task model radar](docs/assets/charts/episode128_task_model_radar.svg)
 
-The single-episode radar isolates Minimal vs Neural MLP, both with 20/20 scored
-public-sample axes. The 128-episode radar isolates metadata/raw baselines,
-Qwen3-Omni v6 LoRA, Cosmos3-Super Reasoner, and Cosmos3-Nano Future Window:
-metadata and raw-feature simple/NN baselines are now complete 20/20
-multi-episode records, with documented compact proxy notes where the public
-export lacks the original raw target. The current matrix has 180/180 scored
-method-task records.
+The single-episode radar uses one enlarged panel for Minimal vs Neural MLP, both
+with 20/20 scored public-sample axes. The 128-episode radar uses three grouped
+panels for metadata/text baselines, raw-feature baselines, and foundation-model
+rows: metadata and raw-feature simple/NN baselines are now complete 20/20
+multi-episode records, and Qwen3-Omni v6 LoRA, Cosmos3-Super Reasoner, and
+Cosmos3-Nano Future Window each carry 20 scored task records. The current matrix
+has 180/180 scored method-task records.
 
 The website raw sample browser includes a concise stream-to-feature ledger
 backed by [`docs/data/modality_atlas.json`](docs/data/modality_atlas.json) and
@@ -887,7 +886,7 @@ scripts/
   research_direction_extension_tasks.py # one extra data-backed probe per track
   tier2_task_suite.py              # historical-name provenance builder for unified task rows
   build_unified_task_suite.py       # builds TASK_SUITE_20.md and task_suite_20.json
-  build_unified_task_model_radar.py # builds the unified 20-axis model comparison chart
+  build_unified_task_model_radar.py # builds grouped 20-axis model comparison radars
   build_task_method_20_gap_audit.py # builds the explicit 180/180 scored-cell ledger
   task_walkthroughs.py              # human-readable task-card and walkthrough-storyboard metadata
   generate_visualizations.py        # refreshes SVG charts + summary JSON
@@ -930,9 +929,9 @@ docs/
   data/additional_development_directions.json # concrete non-backbone project directions
   data/summary_metrics.json         # website-readable metrics bundle
   data/task_suite_20.json           # unified 20-task suite bundle
-  data/unified_task_model_radar.json # 20-task radar values and method overlays
-  data/single_episode_task_model_radar.json # 1-episode split radar values
-  data/episode128_task_model_radar.json # 128-episode split radar values
+  data/unified_task_model_radar.json # 20-task radar values, groups, and sources
+  data/single_episode_task_model_radar.json # 1-episode grouped radar values
+  data/episode128_task_model_radar.json # 128-episode grouped radar values
   data/task_method_20_result_matrix.json # 9-method x 20-task result matrix
   data/task_method_20_gap_audit.json # explicit 180/180 scored-cell ledger
   data/evidence_contract.json       # machine-readable project scope
@@ -955,9 +954,9 @@ docs/
   assets/pipeline_diagram.png       # verified episode pipeline graphic
   assets/qwen3_omni_lora_pipeline.png # Qwen3-Omni LoRA training-flow figure
   assets/task_architectures.png     # verified task-head architecture map
-  assets/charts/unified_task_model_radar.svg # 20-task minimal/NN/Qwen3-Omni/Cosmos3 radar
-  assets/charts/single_episode_task_model_radar.svg # 1-episode split radar
-  assets/charts/episode128_task_model_radar.svg # 128-episode split radar
+  assets/charts/unified_task_model_radar.svg # 9-method grouped small-multiple radar board
+  assets/charts/single_episode_task_model_radar.svg # 1-episode enlarged radar panel
+  assets/charts/episode128_task_model_radar.svg # 128-episode grouped radar panels
   assets/charts/*.svg               # regenerated visualizations
 
 notes/

TASK_METHOD_20_RESULT_MATRIX.md

@@ -18,7 +18,7 @@ Legend: `score` = direct numeric task score and `proxy` = documented compact sub
 
 ## Compact Score Matrix
 
-Cells show `raw metric value`, then `direct/proxy; normalized radar value; metric key`. The raw metric is the value to cite; the normalized value is the 0-1 plotting value used by the radar.
+Cells show `raw metric value`, then `direct/proxy; normalized radar value; metric key`. The raw metric is the value to cite; the normalized value is the exact linear 0-1 score retained in JSON. The SVG radar uses sqrt(normalized score) only for visual radius, so low but real differences remain visible without changing the table values.
 
 | # | Task | Min | NN | 128-S | 128-NN | 128-RS | 128-RN | Qwen3 | C3-S | C3-N |
 | ---: | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |

data/figure_index.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Figure Index",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:19:00+00:00",
+  "generated_at_utc": "2026-06-21T20:35:17+00:00",
   "scope": "Public figures, diagrams, charts, and derived modality thumbnails. Raw Xperience-10M videos, annotations, RRD files, and Qwen weights are excluded.",
   "figure_count": 29,
   "figures": [
@@ -406,17 +406,17 @@
       "id": "unified_task_model_radar",
       "title": "Unified 20-task model radar",
       "path": "docs/assets/charts/unified_task_model_radar.svg",
-      "role": "Twenty-axis direction-aware comparison of minimal and neural MLP baselines, with 128-episode metadata, Qwen3, and Cosmos task-aligned overlay points and branch notes.",
+      "role": "Grouped small-multiple 20-task radar board for all nine methods, separating single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows while preserving task keys and proxy notes.",
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 57938,
-      "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8",
+      "bytes": 98527,
+      "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },
@@ -428,13 +428,13 @@
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 35232,
-      "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e",
+      "bytes": 36930,
+      "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },
@@ -442,17 +442,17 @@
       "id": "episode128_task_model_radar",
       "title": "128-episode 20-task model radar",
       "path": "docs/assets/charts/episode128_task_model_radar.svg",
-      "role": "Twenty-axis split radar for selected 128-episode methods: raw-feature simple/NN as complete scored polygons plus metadata, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano task-aligned overlays.",
+      "role": "Grouped 20-task radar for selected 128-episode methods: metadata/text baselines, raw-feature simple/NN, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano with local legends and proxy notes.",
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 51915,
-      "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4",
+      "bytes": 79370,
+      "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },

data/mirror_parity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:00:18+00:00",
+  "generated_at_utc": "2026-06-21T20:33:57+00:00",
   "hf_root": "hf_publish",
   "summary": {
     "group_count": 1258,
@@ -138,45 +138,45 @@
       "local": {
         "path": "repo:docs/data/artifact_index.json",
         "exists": true,
-        "bytes": 124341,
-        "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+        "bytes": 124471,
+        "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model_data": {
           "path": "hf_model:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model": {
           "path": "hf_model:metrics/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         }
       },
       "failures": []
@@ -334,45 +334,45 @@
       "local": {
         "path": "repo:docs/data/figure_index.json",
         "exists": true,
-        "bytes": 19485,
-        "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+        "bytes": 19526,
+        "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model_data": {
           "path": "hf_model:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model": {
           "path": "hf_model:metrics/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         }
       },
       "failures": []
@@ -972,44 +972,44 @@
         "path": "repo:docs/data/publication_audit.json",
         "exists": true,
         "bytes": 10940,
-        "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+        "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model_data": {
           "path": "hf_model:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model": {
           "path": "hf_model:metrics/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         }
       },
       "failures": []
@@ -1021,44 +1021,44 @@
         "path": "repo:docs/data/public_surface_qa.json",
         "exists": true,
         "bytes": 7693,
-        "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+        "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model_data": {
           "path": "hf_model:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model": {
           "path": "hf_model:metrics/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         }
       },
       "failures": []
@@ -1217,44 +1217,44 @@
         "path": "repo:docs/data/quality_gates.json",
         "exists": true,
         "bytes": 8640,
-        "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+        "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model_data": {
           "path": "hf_model:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model": {
           "path": "hf_model:metrics/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         }
       },
       "failures": []
@@ -1658,44 +1658,44 @@
         "path": "repo:docs/data/scope_claims_audit.json",
         "exists": true,
         "bytes": 21313,
-        "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+        "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model_data": {
           "path": "hf_model:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model": {
           "path": "hf_model:metrics/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         }
       },
       "failures": []
@@ -1756,44 +1756,44 @@
         "path": "repo:docs/data/source_alignment_audit.json",
         "exists": true,
         "bytes": 4432,
-        "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+        "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model_data": {
           "path": "hf_model:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model": {
           "path": "hf_model:metrics/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         }
       },
       "failures": []
@@ -1853,45 +1853,45 @@
       "local": {
         "path": "repo:docs/data/single_episode_task_model_radar.json",
         "exists": true,
-        "bytes": 51327,
-        "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+        "bytes": 52866,
+        "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model_data": {
           "path": "hf_model:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model": {
           "path": "hf_model:metrics/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         }
       },
       "failures": []
@@ -1902,45 +1902,45 @@
       "local": {
         "path": "repo:docs/data/episode128_task_model_radar.json",
         "exists": true,
-        "bytes": 185212,
-        "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+        "bytes": 186997,
+        "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model_data": {
           "path": "hf_model:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model": {
           "path": "hf_model:metrics/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         }
       },
       "failures": []
@@ -2197,44 +2197,44 @@
         "path": "repo:docs/data/task_surface_integrity.json",
         "exists": true,
         "bytes": 46246,
-        "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+        "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         }
       },
       "failures": []
@@ -2294,45 +2294,45 @@
       "local": {
         "path": "repo:docs/data/task_method_20_result_matrix.json",
         "exists": true,
-        "bytes": 128509,
-        "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+        "bytes": 128991,
+        "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         }
       },
       "failures": []
@@ -2490,45 +2490,45 @@
       "local": {
         "path": "repo:docs/data/unified_task_model_radar.json",
         "exists": true,
-        "bytes": 229035,
-        "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+        "bytes": 230938,
+        "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model_data": {
           "path": "hf_model:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model": {
           "path": "hf_model:metrics/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         }
       },
       "failures": []
@@ -2540,44 +2540,44 @@
         "path": "repo:docs/data/website_integrity.json",
         "exists": true,
         "bytes": 20178,
-        "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+        "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model_data": {
           "path": "hf_model:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model": {
           "path": "hf_model:metrics/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         }
       },
       "failures": []
@@ -2760,33 +2760,33 @@
       "local": {
         "path": "repo:docs/assets/charts/single_episode_task_model_radar.svg",
         "exists": true,
-        "bytes": 35232,
-        "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+        "bytes": 36930,
+        "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         }
       },
       "failures": []
@@ -2797,33 +2797,33 @@
       "local": {
         "path": "repo:docs/assets/charts/episode128_task_model_radar.svg",
         "exists": true,
-        "bytes": 51915,
-        "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+        "bytes": 79370,
+        "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         }
       },
       "failures": []
@@ -2871,33 +2871,33 @@
       "local": {
         "path": "repo:docs/assets/charts/unified_task_model_radar.svg",
         "exists": true,
-        "bytes": 57938,
-        "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+        "bytes": 98527,
+        "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         }
       },
       "failures": []
@@ -5327,21 +5327,21 @@
       "local": {
         "path": "repo:scripts/build_artifact_index.py",
         "exists": true,
-        "bytes": 68279,
-        "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+        "bytes": 68407,
+        "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 68279,
-          "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+          "bytes": 68407,
+          "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 68279,
-          "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+          "bytes": 68407,
+          "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
         }
       },
       "failures": []
@@ -5402,21 +5402,21 @@
       "local": {
         "path": "repo:scripts/build_figure_index.py",
         "exists": true,
-        "bytes": 16845,
-        "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+        "bytes": 16886,
+        "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_figure_index.py",
           "exists": true,
-          "bytes": 16845,
-          "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+          "bytes": 16886,
+          "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_figure_index.py",
           "exists": true,
-          "bytes": 16845,
-          "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+          "bytes": 16886,
+          "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
         }
       },
       "failures": []
@@ -5877,21 +5877,21 @@
       "local": {
         "path": "repo:scripts/build_unified_task_model_radar.py",
         "exists": true,
-        "bytes": 69956,
-        "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+        "bytes": 78735,
+        "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_unified_task_model_radar.py",
           "exists": true,
-          "bytes": 69956,
-          "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+          "bytes": 78735,
+          "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_unified_task_model_radar.py",
           "exists": true,
-          "bytes": 69956,
-          "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+          "bytes": 78735,
+          "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
         }
       },
       "failures": []
@@ -6331,39 +6331,39 @@
       "local": {
         "path": "repo:docs/index.html",
         "exists": true,
-        "bytes": 348267,
-        "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+        "bytes": 348384,
+        "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_artifacts_root": {
           "path": "hf_artifacts:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_model": {
           "path": "hf_model:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_model_docs": {
           "path": "hf_model:docs/index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         }
       },
       "failures": []
@@ -31027,27 +31027,27 @@
       "local": {
         "path": "repo:FIGURE_INDEX.md",
         "exists": true,
-        "bytes": 7027,
-        "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+        "bytes": 7068,
+        "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         },
         "hf_model": {
           "path": "hf_model:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         }
       },
       "failures": []
@@ -31554,27 +31554,27 @@
       "local": {
         "path": "repo:TASK_METHOD_20_RESULT_MATRIX.md",
         "exists": true,
-        "bytes": 14715,
-        "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+        "bytes": 14862,
+        "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         },
         "hf_model": {
           "path": "hf_model:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         }
       },
       "failures": []

data/publication_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:02:09+00:00",
+  "generated_at_utc": "2026-06-21T20:35:41+00:00",
   "checks": [
     {
       "name": "required_publication_assets_present",

data/unified_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "Unified 20-Task Model Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
@@ -10,10 +10,53 @@
     "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",
     "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
+    "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
     "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
-    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 points are plotted only on task-aligned axes. Scoreless records mean the public result does not evaluate that task contract.",
-    "metadata_128_overlay": "128-episode aligned baselines have 20 records. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists; raw interaction text and paired camera-view embeddings remain explicit gaps.",
-    "raw_128_overlay": "128-episode raw-feature baselines use staged sensor NPZ features. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
+    "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
+    "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+  },
+  "chart_design": {
+    "mode": "grouped_small_multiples",
+    "method_count": 9,
+    "reason": "The public release has nine methods and 180 scored records; small-multiple radar panels avoid a nine-polygon overlay while keeping every method visible.",
+    "groups": [
+      {
+        "id": "single_episode",
+        "title": "Single-episode sample",
+        "series_ids": [
+          "minimal",
+          "neural_mlp"
+        ]
+      },
+      {
+        "id": "metadata_128",
+        "title": "128-episode metadata/text",
+        "series_ids": [
+          "metadata128_simple",
+          "metadata128_neural_mlp"
+        ]
+      },
+      {
+        "id": "raw_128",
+        "title": "128-episode raw features",
+        "series_ids": [
+          "raw128_simple",
+          "raw128_neural_mlp"
+        ]
+      },
+      {
+        "id": "foundation_models",
+        "title": "Foundation-model probes",
+        "series_ids": [
+          "qwen3_omni_v6_lora",
+          "cosmos3_super_reasoner",
+          "cosmos3_nano_future_window"
+        ]
+      }
+    ],
+    "visual_radius_transform": "sqrt(normalized_score)",
+    "exact_value_source": "docs/data/task_method_20_result_matrix.json"
   },
   "series": [
     {
@@ -25,7 +68,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode simple heads over the public sample split.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -48,7 +91,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -71,7 +114,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "9 6",
       "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -95,7 +138,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "3 6",
       "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -119,7 +162,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "8 4",
       "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -143,7 +186,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "2 5",
       "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -167,7 +210,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
       "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -190,7 +233,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
       "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -213,7 +256,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "2 7",
       "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

docs/data/artifact_index.json

@@ -1,6 +1,6 @@
 {
   "title": "Ropedia Xperience-10M Task Suite Artifact Index",
-  "generated_at_utc": "2026-06-21T15:19:00+00:00",
+  "generated_at_utc": "2026-06-21T20:35:18+00:00",
   "status": "pass",
   "artifact_count": 228,
   "missing": [],
@@ -92,8 +92,8 @@
       "surface": "repo_hf",
       "shows": "Defines terminology that can be confused across data scope, task metrics, model branches, and public mirrors.",
       "exists": true,
-      "bytes": 10220,
-      "sha256": "c3723a3dfaf902f4bc2527b78d11057ab8ba01c6b9715fa873c7dd819deddf81"
+      "bytes": 10857,
+      "sha256": "b9b8f8695b6c211e849073e1634057f158877a61161eca05b1266769158ee83e"
     },
     {
       "id": "glossary_json",
@@ -103,8 +103,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable terminology layer for the website, artifact dataset, model mirror, and public QA checks.",
       "exists": true,
-      "bytes": 17380,
-      "sha256": "3ba746413eb4a7d2646333e3746e0b3f4039db61d03c159d2d059fecfe4b51ed"
+      "bytes": 18754,
+      "sha256": "b1dc42e1f42a7c19bb4b2ebd32a0862df28bec671eaa849b09a97f103675e9eb"
     },
     {
       "id": "research_roadmap",
@@ -158,8 +158,8 @@
       "surface": "repo_hf",
       "shows": "Frames spatial intelligence, human-video world modeling, and vision-language-action as three pipeline tracks with explicit inputs, outputs, maturity, and next evidence gates.",
       "exists": true,
-      "bytes": 8008,
-      "sha256": "abd179631f1d204328fa5a2e018207eceeb7d46be12b7dab2826e70dfde97130"
+      "bytes": 11609,
+      "sha256": "69d4d8781015c807c58a720b3bf967ee872540a2fe2b7e7973105946c5a1cf11"
     },
     {
       "id": "three_foundation_pipelines_json",
@@ -169,8 +169,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable pipeline-track contract for the website and Hugging Face mirrors.",
       "exists": true,
-      "bytes": 10312,
-      "sha256": "9eb30d098f1b3787255a5506e4299f2cd4904ef989f2eaeaa2e5f77519c17378"
+      "bytes": 14465,
+      "sha256": "c8c9b7a9ee8d3ecfe8662cf0336a7ca2ade6d670c5567d2a50dfb67c7241defd"
     },
     {
       "id": "spatial_intelligence_slide_diagram",
@@ -632,7 +632,7 @@
       "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
       "exists": true,
       "bytes": 4432,
-      "sha256": "5ab2ea4bfefe9f5bc7854f02b2e1e2b5206766a54447647191828da1a1a2077c"
+      "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
     },
     {
       "id": "source_alignment_validator",
@@ -653,8 +653,8 @@
       "surface": "repo_hf",
       "shows": "Publishes prepared Space, artifact dataset, and model bundles, including an explicit model-binary upload batch.",
       "exists": true,
-      "bytes": 25115,
-      "sha256": "31866958ffaa3954f1bc4f920fbf80d5b41fd95228be50989dadb6e8cbe619e3"
+      "bytes": 29935,
+      "sha256": "89ed1b25784cd42f19f2e4731eaa52e8655e8ed06cc2a12b6a2c0add027c5fc0"
     },
     {
       "id": "github_package_dockerfile",
@@ -697,8 +697,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable protocol generated from committed task metrics for website and HF mirrors.",
       "exists": true,
-      "bytes": 24047,
-      "sha256": "d8f61b646a2f3f1e0af901dbdaff310ebfeea90622c93a34b9e35f34be98b896"
+      "bytes": 24267,
+      "sha256": "83289b52e0193fa86d63fac7dd8af98d0612199b1e1a5f5ed37014baa9168656"
     },
     {
       "id": "evaluation_protocol_builder",
@@ -708,8 +708,8 @@
       "surface": "repo_hf",
       "shows": "Regenerates the protocol from committed summary metrics and task artifacts.",
       "exists": true,
-      "bytes": 19825,
-      "sha256": "aa9de1582f8fa79c1850e10e69fb125c0e3c1add433c7ebedc104c2efb42272e"
+      "bytes": 19845,
+      "sha256": "b5d888fd67ba6b8150b24960aa0858db50f16a5c7b59a8ce274401e384f0a2a3"
     },
     {
       "id": "task_suite_20",
@@ -730,8 +730,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable unified 20-task index for the website, Hugging Face mirrors, and live verification.",
       "exists": true,
-      "bytes": 34585,
-      "sha256": "75145285cf71bc3bb9a10377a1921b60e85c4546dc8b858102b3c26e94c11a01"
+      "bytes": 34805,
+      "sha256": "5d7a3b5b57e64980291b3ce6a8741b0b822e94bd447ca95519d1da7040923476"
     },
     {
       "id": "task_suite_20_builder",
@@ -741,8 +741,8 @@
       "surface": "repo_hf",
       "shows": "Regenerates the unified 20-task JSON and Markdown from the public-sample metrics plus the historical provenance result bundle.",
       "exists": true,
-      "bytes": 12157,
-      "sha256": "157265b5c025f279ce1eb56c52dd720ce0969b8426d5887030bfa179a3b565e0"
+      "bytes": 12129,
+      "sha256": "4c2550c657bfa5bc37e21e78e7e27dd70daa3b178c8ffb3191e52f835221713a"
     },
     {
       "id": "unified_task_model_radar_json",
@@ -750,10 +750,10 @@
       "path": "docs/data/unified_task_model_radar.json",
       "kind": "website_data",
       "surface": "website_hf",
-      "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3-Omni/Cosmos3 overlay mappings, method-card caveats, proxy flags, and source artifacts.",
+      "shows": "Stores normalized 20-axis radar values, raw task metrics, grouped chart-design metadata, Qwen3-Omni/Cosmos3 source mappings, method-card caveats, proxy flags, and source artifacts.",
       "exists": true,
-      "bytes": 228815,
-      "sha256": "862376178e8b0d01b536f49a18b7934a373494f8b36080790f616438ec0e035e"
+      "bytes": 230938,
+      "sha256": "bd7b8fd8a169273c5cec2beab050a583307dcc64e5e3fefcd690484b4a0754bc"
     },
     {
       "id": "single_episode_task_model_radar_json",
@@ -763,8 +763,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
       "exists": true,
-      "bytes": 51107,
-      "sha256": "5f2ebb41e8488446ea5c5cd2cb75bbedce688433feffe1412288de56b133bd5c"
+      "bytes": 52256,
+      "sha256": "f282dc0c4c654fe6f2cd646612fd0942d267dec60c6143cc36688edbc27c13da"
     },
     {
       "id": "episode128_task_model_radar_json",
@@ -774,8 +774,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines, Qwen3-Omni v6, Cosmos3-Super, and Cosmos3-Nano, now complete at 140/140 scored rows with proxy notes retained.",
       "exists": true,
-      "bytes": 184992,
-      "sha256": "385704db90443d74903f365e90b27538020f5574c96f296bbf63173f488a645d"
+      "bytes": 186828,
+      "sha256": "f904cf9eb3160a50e4469989e44557e77d710e459f812ba7b194d0ed8d9746bd"
     },
     {
       "id": "task_method_20_result_matrix_json",
@@ -785,8 +785,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and the current release is complete at 180/180 scored rows.",
       "exists": true,
-      "bytes": 128509,
-      "sha256": "96082daa33771963ac40b7d719df00a76ec443508a3d3101cb6dd82d87965729"
+      "bytes": 128991,
+      "sha256": "bacb549e64b6d1936b55fe7593cfbaeb1dbf5bfe824c8507ea75e493230212fe"
     },
     {
       "id": "task_method_20_result_matrix",
@@ -796,8 +796,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing table that separates 20 records per method, direct numeric scores, documented compact-proxy scores, and source artifacts.",
       "exists": true,
-      "bytes": 3563,
-      "sha256": "84b21bd3359e6149b952a9b3b6991f7ba8ff412390a92983bd6d59f212d58316"
+      "bytes": 14862,
+      "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
     },
     {
       "id": "task_method_20_gap_audit_json",
@@ -808,7 +808,7 @@
       "shows": "Machine-readable 180-record completion ledger with numeric scores, proxy flags, explicit status reasons, and source artifacts.",
       "exists": true,
       "bytes": 8500,
-      "sha256": "5743354519dfae924d973ffca90a5d1ef4b0c316cf201b3ac443f6b5d4600de5"
+      "sha256": "4f5cc7a29fe030a9fd5b97893ac67454ebc6287f5942aeedb2bfca71c411332d"
     },
     {
       "id": "task_method_20_gap_audit",
@@ -819,7 +819,7 @@
       "shows": "Reader-facing ledger confirming 180/180 scored method-task cells and listing the six compact-proxy records separately.",
       "exists": true,
       "bytes": 3417,
-      "sha256": "01f47c74db965887e55f17b674e1617e396dd01a51fdc7bf9a9c7612f5596b2c"
+      "sha256": "b094732dd98c904ea0ab30e741576a3d5eeb8ca07e7a494e459b11e31320ae4d"
     },
     {
       "id": "task_method_20_source_audit_json",
@@ -830,7 +830,7 @@
       "shows": "Machine-readable check that scored JSON-backed matrix cells match their declared metric source values.",
       "exists": true,
       "bytes": 561,
-      "sha256": "bb50000bb681f1ed12c4089bd3541f14b8e121ea5a1fe06e1a6a559cb8960e0b"
+      "sha256": "1bc6bb15ab45e73ada4d3c2d1ec326cffd9c6bc6d6d791c7468b3ed16881a463"
     },
     {
       "id": "task_method_20_source_audit",
@@ -841,7 +841,7 @@
       "shows": "Reader-facing source-value audit for the 180-result matrix.",
       "exists": true,
       "bytes": 447,
-      "sha256": "1a0583629368cee3abadc49d4a0220dead924326a04e82b3a22a9fc6d6b0d252"
+      "sha256": "7f5e80d6dcd66be1c6b2c63144adb64d0cdad0008884ebd8f015388545e4b914"
     },
     {
       "id": "two_evidence_line_map_chart",
@@ -860,10 +860,10 @@
       "path": "docs/assets/charts/unified_task_model_radar.svg",
       "kind": "generated_figure",
       "surface": "website_hf",
-      "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3-Omni and Cosmos3 task-aligned overlays.",
+      "shows": "Groups all nine methods into small-multiple 20-task radar panels so single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows remain readable.",
       "exists": true,
-      "bytes": 57938,
-      "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+      "bytes": 98527,
+      "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
     },
     {
       "id": "single_episode_task_model_radar_chart",
@@ -871,10 +871,10 @@
       "path": "docs/assets/charts/single_episode_task_model_radar.svg",
       "kind": "generated_figure",
       "surface": "website_hf",
-      "shows": "Separates the one-episode Minimal and Neural MLP 20/20 scored baselines into a clean two-polygon radar.",
+      "shows": "Shows the one-episode Minimal and Neural MLP 20/20 scored baselines in one enlarged radar panel with local legend and task key.",
       "exists": true,
-      "bytes": 35232,
-      "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+      "bytes": 36930,
+      "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
     },
     {
       "id": "episode128_task_model_radar_chart",
@@ -882,10 +882,10 @@
       "path": "docs/assets/charts/episode128_task_model_radar.svg",
       "kind": "generated_figure",
       "surface": "website_hf",
-      "shows": "Separates the selected 128-episode methods: raw-feature simple/NN as complete 20/20 scored polygons plus metadata, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano task-aligned overlays.",
+      "shows": "Separates selected 128-episode methods into metadata/text, raw-feature, and foundation-model radar panels with all 140 result rows scored and proxy notes retained.",
       "exists": true,
-      "bytes": 51915,
-      "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+      "bytes": 79370,
+      "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
     },
     {
       "id": "unified_task_model_radar_builder",
@@ -893,10 +893,10 @@
       "path": "scripts/build_unified_task_model_radar.py",
       "kind": "visualization_builder",
       "surface": "repo_hf",
-      "shows": "Regenerates the direction-aware radar chart and machine-readable metric overlay JSON.",
+      "shows": "Regenerates grouped 20-task radar charts plus machine-readable metric, source, chart-design, and proxy metadata.",
       "exists": true,
-      "bytes": 68610,
-      "sha256": "96bc2df0de5a9e512d69961ddb13ea87b26ef01f1f943f5a78a6dc373400949d"
+      "bytes": 79396,
+      "sha256": "78949d7030cf6995edbb1d46a35692c7fe835d102df619cdf8c9d8ea9c5318e2"
     },
     {
       "id": "task_method_20_gap_audit_builder",
@@ -1093,8 +1093,8 @@
       "surface": "repo_hf",
       "shows": "Catalogs public figures, charts, modality thumbnails, dimensions, hashes, roles, and source scripts.",
       "exists": true,
-      "bytes": 7027,
-      "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+      "bytes": 7068,
+      "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
     },
     {
       "id": "figure_index_json",
@@ -1104,8 +1104,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable visual asset index for website and Hugging Face mirrors.",
       "exists": true,
-      "bytes": 19485,
-      "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+      "bytes": 19526,
+      "sha256": "601acd715891bb148b0a1706573a2fdb015ca3c5967f02a169577b483b0dcd43"
     },
     {
       "id": "figure_index_builder",
@@ -1115,8 +1115,8 @@
       "surface": "repo_hf",
       "shows": "Regenerates visual-asset hashes, dimensions, and source-script provenance.",
       "exists": true,
-      "bytes": 16845,
-      "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+      "bytes": 16886,
+      "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
     },
     {
       "id": "brand_assets_json",
@@ -1182,7 +1182,7 @@
       "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
       "exists": true,
       "bytes": 8640,
-      "sha256": "6e54f6828b8fef97e963a9a56bccc91162b8a632f6897743095e32407fa0db98"
+      "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
     },
     {
       "id": "public_surface_qa",
@@ -1226,7 +1226,7 @@
       "volatile": true,
       "shows": "Machine-readable report for SEO/social metadata, accessible tab semantics, public links, project links, and clear project presentation.",
       "exists": true,
-      "bytes": 7691,
+      "bytes": 7693,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1318,8 +1318,8 @@
       "surface": "repo",
       "shows": "Fetches the published GitHub/HF URLs and compares live hashes and public-card markers against the release assets.",
       "exists": true,
-      "bytes": 69151,
-      "sha256": "c4af8644d50dafe7d4249dd7c5b36bb19e996628ff6d8436fbb6e027da526c1f"
+      "bytes": 69123,
+      "sha256": "a96d0a95ea1da54fb8b6a95b2c91d4a067eef8358d825c44d919e66d78ecb8f7"
     },
     {
       "id": "reproducibility_contract",
@@ -1351,8 +1351,8 @@
       "surface": "repo_hf",
       "shows": "Generates the selective artifact catalog from local files.",
       "exists": true,
-      "bytes": 68279,
-      "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+      "bytes": 68407,
+      "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
     },
     {
       "id": "publication_audit",
@@ -1363,7 +1363,7 @@
       "volatile": true,
       "shows": "Confirms public bundles exclude raw data, caches, heavy archives, and credential text.",
       "exists": true,
-      "bytes": 10939,
+      "bytes": 10940,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1387,7 +1387,7 @@
       "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": 1420743,
+      "bytes": 1420751,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1399,7 +1399,7 @@
       "volatile": true,
       "shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
       "exists": true,
-      "bytes": 20760,
+      "bytes": 20178,
       "hash_policy": "existence_and_size_only"
     },
     {

docs/data/episode128_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "128-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+00:00",
   "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3-Omni v6, Cosmos3-Super, and Cosmos3-Nano diagnostics. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.",
   "task_count": 20,
   "method_count": 7,
@@ -11,10 +11,45 @@
     "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",
     "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
+    "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
     "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
-    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 points are plotted only on task-aligned axes. Scoreless records mean the public result does not evaluate that task contract.",
-    "metadata_128_overlay": "128-episode aligned baselines have 20 records. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists; raw interaction text and paired camera-view embeddings remain explicit gaps.",
-    "raw_128_overlay": "128-episode raw-feature baselines use staged sensor NPZ features. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
+    "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
+    "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+  },
+  "chart_design": {
+    "mode": "grouped_small_multiples",
+    "method_count": 7,
+    "reason": "This split view has 7 methods and 140 method-task records; grouped radar panels keep related methods readable while retaining the unified source matrix.",
+    "groups": [
+      {
+        "id": "metadata_128",
+        "title": "128-episode metadata/text",
+        "series_ids": [
+          "metadata128_simple",
+          "metadata128_neural_mlp"
+        ]
+      },
+      {
+        "id": "raw_128",
+        "title": "128-episode raw features",
+        "series_ids": [
+          "raw128_simple",
+          "raw128_neural_mlp"
+        ]
+      },
+      {
+        "id": "foundation_models",
+        "title": "Foundation-model probes",
+        "series_ids": [
+          "qwen3_omni_v6_lora",
+          "cosmos3_super_reasoner",
+          "cosmos3_nano_future_window"
+        ]
+      }
+    ],
+    "visual_radius_transform": "sqrt(normalized_score)",
+    "exact_value_source": "docs/data/task_method_20_result_matrix.json"
   },
   "source_unified_radar": "docs/data/unified_task_model_radar.json",
   "source_result_matrix": "docs/data/task_method_20_result_matrix.json",
@@ -28,7 +63,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "9 6",
       "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -52,7 +87,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "3 6",
       "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -76,7 +111,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "8 4",
       "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -100,7 +135,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "2 5",
       "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -124,7 +159,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
       "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -147,7 +182,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
       "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -170,7 +205,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "2 7",
       "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

docs/data/figure_index.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Figure Index",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:19:00+00:00",
+  "generated_at_utc": "2026-06-21T20:35:17+00:00",
   "scope": "Public figures, diagrams, charts, and derived modality thumbnails. Raw Xperience-10M videos, annotations, RRD files, and Qwen weights are excluded.",
   "figure_count": 29,
   "figures": [
@@ -406,17 +406,17 @@
       "id": "unified_task_model_radar",
       "title": "Unified 20-task model radar",
       "path": "docs/assets/charts/unified_task_model_radar.svg",
-      "role": "Twenty-axis direction-aware comparison of minimal and neural MLP baselines, with 128-episode metadata, Qwen3, and Cosmos task-aligned overlay points and branch notes.",
+      "role": "Grouped small-multiple 20-task radar board for all nine methods, separating single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows while preserving task keys and proxy notes.",
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 57938,
-      "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8",
+      "bytes": 98527,
+      "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },
@@ -428,13 +428,13 @@
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 35232,
-      "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e",
+      "bytes": 36930,
+      "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },
@@ -442,17 +442,17 @@
       "id": "episode128_task_model_radar",
       "title": "128-episode 20-task model radar",
       "path": "docs/assets/charts/episode128_task_model_radar.svg",
-      "role": "Twenty-axis split radar for selected 128-episode methods: raw-feature simple/NN as complete scored polygons plus metadata, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano task-aligned overlays.",
+      "role": "Grouped 20-task radar for selected 128-episode methods: metadata/text baselines, raw-feature simple/NN, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano with local legends and proxy notes.",
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 51915,
-      "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4",
+      "bytes": 79370,
+      "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },

docs/data/mirror_parity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:00:18+00:00",
+  "generated_at_utc": "2026-06-21T20:33:57+00:00",
   "hf_root": "hf_publish",
   "summary": {
     "group_count": 1258,
@@ -138,45 +138,45 @@
       "local": {
         "path": "repo:docs/data/artifact_index.json",
         "exists": true,
-        "bytes": 124341,
-        "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+        "bytes": 124471,
+        "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model_data": {
           "path": "hf_model:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model": {
           "path": "hf_model:metrics/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         }
       },
       "failures": []
@@ -334,45 +334,45 @@
       "local": {
         "path": "repo:docs/data/figure_index.json",
         "exists": true,
-        "bytes": 19485,
-        "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+        "bytes": 19526,
+        "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model_data": {
           "path": "hf_model:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model": {
           "path": "hf_model:metrics/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         }
       },
       "failures": []
@@ -972,44 +972,44 @@
         "path": "repo:docs/data/publication_audit.json",
         "exists": true,
         "bytes": 10940,
-        "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+        "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model_data": {
           "path": "hf_model:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model": {
           "path": "hf_model:metrics/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         }
       },
       "failures": []
@@ -1021,44 +1021,44 @@
         "path": "repo:docs/data/public_surface_qa.json",
         "exists": true,
         "bytes": 7693,
-        "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+        "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model_data": {
           "path": "hf_model:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model": {
           "path": "hf_model:metrics/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         }
       },
       "failures": []
@@ -1217,44 +1217,44 @@
         "path": "repo:docs/data/quality_gates.json",
         "exists": true,
         "bytes": 8640,
-        "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+        "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model_data": {
           "path": "hf_model:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model": {
           "path": "hf_model:metrics/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         }
       },
       "failures": []
@@ -1658,44 +1658,44 @@
         "path": "repo:docs/data/scope_claims_audit.json",
         "exists": true,
         "bytes": 21313,
-        "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+        "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model_data": {
           "path": "hf_model:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model": {
           "path": "hf_model:metrics/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         }
       },
       "failures": []
@@ -1756,44 +1756,44 @@
         "path": "repo:docs/data/source_alignment_audit.json",
         "exists": true,
         "bytes": 4432,
-        "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+        "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model_data": {
           "path": "hf_model:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model": {
           "path": "hf_model:metrics/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         }
       },
       "failures": []
@@ -1853,45 +1853,45 @@
       "local": {
         "path": "repo:docs/data/single_episode_task_model_radar.json",
         "exists": true,
-        "bytes": 51327,
-        "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+        "bytes": 52866,
+        "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model_data": {
           "path": "hf_model:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model": {
           "path": "hf_model:metrics/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         }
       },
       "failures": []
@@ -1902,45 +1902,45 @@
       "local": {
         "path": "repo:docs/data/episode128_task_model_radar.json",
         "exists": true,
-        "bytes": 185212,
-        "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+        "bytes": 186997,
+        "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model_data": {
           "path": "hf_model:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model": {
           "path": "hf_model:metrics/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         }
       },
       "failures": []
@@ -2197,44 +2197,44 @@
         "path": "repo:docs/data/task_surface_integrity.json",
         "exists": true,
         "bytes": 46246,
-        "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+        "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         }
       },
       "failures": []
@@ -2294,45 +2294,45 @@
       "local": {
         "path": "repo:docs/data/task_method_20_result_matrix.json",
         "exists": true,
-        "bytes": 128509,
-        "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+        "bytes": 128991,
+        "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         }
       },
       "failures": []
@@ -2490,45 +2490,45 @@
       "local": {
         "path": "repo:docs/data/unified_task_model_radar.json",
         "exists": true,
-        "bytes": 229035,
-        "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+        "bytes": 230938,
+        "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model_data": {
           "path": "hf_model:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model": {
           "path": "hf_model:metrics/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         }
       },
       "failures": []
@@ -2540,44 +2540,44 @@
         "path": "repo:docs/data/website_integrity.json",
         "exists": true,
         "bytes": 20178,
-        "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+        "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model_data": {
           "path": "hf_model:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model": {
           "path": "hf_model:metrics/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         }
       },
       "failures": []
@@ -2760,33 +2760,33 @@
       "local": {
         "path": "repo:docs/assets/charts/single_episode_task_model_radar.svg",
         "exists": true,
-        "bytes": 35232,
-        "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+        "bytes": 36930,
+        "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         }
       },
       "failures": []
@@ -2797,33 +2797,33 @@
       "local": {
         "path": "repo:docs/assets/charts/episode128_task_model_radar.svg",
         "exists": true,
-        "bytes": 51915,
-        "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+        "bytes": 79370,
+        "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         }
       },
       "failures": []
@@ -2871,33 +2871,33 @@
       "local": {
         "path": "repo:docs/assets/charts/unified_task_model_radar.svg",
         "exists": true,
-        "bytes": 57938,
-        "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+        "bytes": 98527,
+        "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         }
       },
       "failures": []
@@ -5327,21 +5327,21 @@
       "local": {
         "path": "repo:scripts/build_artifact_index.py",
         "exists": true,
-        "bytes": 68279,
-        "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+        "bytes": 68407,
+        "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 68279,
-          "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+          "bytes": 68407,
+          "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 68279,
-          "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+          "bytes": 68407,
+          "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
         }
       },
       "failures": []
@@ -5402,21 +5402,21 @@
       "local": {
         "path": "repo:scripts/build_figure_index.py",
         "exists": true,
-        "bytes": 16845,
-        "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+        "bytes": 16886,
+        "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_figure_index.py",
           "exists": true,
-          "bytes": 16845,
-          "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+          "bytes": 16886,
+          "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_figure_index.py",
           "exists": true,
-          "bytes": 16845,
-          "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+          "bytes": 16886,
+          "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
         }
       },
       "failures": []
@@ -5877,21 +5877,21 @@
       "local": {
         "path": "repo:scripts/build_unified_task_model_radar.py",
         "exists": true,
-        "bytes": 69956,
-        "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+        "bytes": 78735,
+        "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_unified_task_model_radar.py",
           "exists": true,
-          "bytes": 69956,
-          "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+          "bytes": 78735,
+          "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_unified_task_model_radar.py",
           "exists": true,
-          "bytes": 69956,
-          "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+          "bytes": 78735,
+          "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
         }
       },
       "failures": []
@@ -6331,39 +6331,39 @@
       "local": {
         "path": "repo:docs/index.html",
         "exists": true,
-        "bytes": 348267,
-        "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+        "bytes": 348384,
+        "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_artifacts_root": {
           "path": "hf_artifacts:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_model": {
           "path": "hf_model:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_model_docs": {
           "path": "hf_model:docs/index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         }
       },
       "failures": []
@@ -31027,27 +31027,27 @@
       "local": {
         "path": "repo:FIGURE_INDEX.md",
         "exists": true,
-        "bytes": 7027,
-        "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+        "bytes": 7068,
+        "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         },
         "hf_model": {
           "path": "hf_model:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         }
       },
       "failures": []
@@ -31554,27 +31554,27 @@
       "local": {
         "path": "repo:TASK_METHOD_20_RESULT_MATRIX.md",
         "exists": true,
-        "bytes": 14715,
-        "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+        "bytes": 14862,
+        "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         },
         "hf_model": {
           "path": "hf_model:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         }
       },
       "failures": []

docs/data/public_surface_qa.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Public Project Surface",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:01:39+00:00",
+  "generated_at_utc": "2026-06-21T20:35:18+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": "2026-06-21T20:01:18+00:00"
+          "generated_at_utc": "2026-06-21T20:35:18+00:00"
         },
         "rendered_site_check": {
           "exists": true,
@@ -28,27 +28,27 @@
         "task_surface_integrity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T15:21:55+00:00"
+          "generated_at_utc": "2026-06-21T20:30:48+00:00"
         },
         "source_alignment": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T15:21:55+00:00"
+          "generated_at_utc": "2026-06-21T20:30:47+00:00"
         },
         "scale_up_status": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T15:23:13+00:00"
+          "generated_at_utc": "2026-06-21T20:30:47+00:00"
         },
         "publication_package": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T19:57:53+00:00"
+          "generated_at_utc": "2026-06-21T20:32:45+00:00"
         },
         "mirror_parity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T20:00:18+00:00"
+          "generated_at_utc": "2026-06-21T20:33:57+00:00"
         }
       },
       "failures": {}
@@ -97,8 +97,8 @@
       "marker_counts": {
         "Ropedia Xperience-10M Task Suite": 22,
         "Xperience-10M": 173,
-        "20-task": 110,
-        "Qwen3-Omni": 246,
+        "20-task": 107,
+        "Qwen3-Omni": 239,
         "128-episode pilot": 1
       }
     },

docs/data/publication_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:02:09+00:00",
+  "generated_at_utc": "2026-06-21T20:35:41+00:00",
   "checks": [
     {
       "name": "required_publication_assets_present",

docs/data/quality_gates.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Release Checks",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:21:42+00:00",
+  "generated_at_utc": "2026-06-21T20:35:18+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": "2026-06-21T15:23:13+00:00",
+  "generated_at_utc": "2026-06-21T20:35:22+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": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+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,
@@ -11,10 +11,28 @@
     "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",
     "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
+    "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
     "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
-    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 points are plotted only on task-aligned axes. Scoreless records mean the public result does not evaluate that task contract.",
-    "metadata_128_overlay": "128-episode aligned baselines have 20 records. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists; raw interaction text and paired camera-view embeddings remain explicit gaps.",
-    "raw_128_overlay": "128-episode raw-feature baselines use staged sensor NPZ features. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
+    "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
+    "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+  },
+  "chart_design": {
+    "mode": "grouped_small_multiples",
+    "method_count": 2,
+    "reason": "This split view has 2 methods and 40 method-task records; grouped radar panels keep related methods readable while retaining the unified source matrix.",
+    "groups": [
+      {
+        "id": "single_episode",
+        "title": "Single-episode sample",
+        "series_ids": [
+          "minimal",
+          "neural_mlp"
+        ]
+      }
+    ],
+    "visual_radius_transform": "sqrt(normalized_score)",
+    "exact_value_source": "docs/data/task_method_20_result_matrix.json"
   },
   "source_unified_radar": "docs/data/unified_task_model_radar.json",
   "source_result_matrix": "docs/data/task_method_20_result_matrix.json",
@@ -28,7 +46,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode simple heads over the public sample split.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -51,7 +69,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

docs/data/source_alignment_audit.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Source Alignment Note",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:21:55+00:00",
+  "generated_at_utc": "2026-06-21T20:35:22+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

@@ -1,7 +1,7 @@
 {
   "title": "Task Method 20-Result Matrix",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
@@ -16,7 +16,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode simple heads over the public sample split.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -39,7 +39,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -62,7 +62,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "9 6",
       "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -86,7 +86,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "3 6",
       "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -110,7 +110,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "8 4",
       "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -134,7 +134,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "2 5",
       "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -158,7 +158,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
       "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -181,7 +181,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
       "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -204,7 +204,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "2 7",
       "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

docs/data/task_surface_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:21:55+00:00",
+  "generated_at_utc": "2026-06-21T20:35:22+00:00",
   "summary": {
     "original_walkthrough_task_count": 12,
     "expected_original_walkthrough_task_count": 12,

docs/data/unified_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "Unified 20-Task Model Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
@@ -10,10 +10,53 @@
     "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",
     "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
+    "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
     "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
-    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 points are plotted only on task-aligned axes. Scoreless records mean the public result does not evaluate that task contract.",
-    "metadata_128_overlay": "128-episode aligned baselines have 20 records. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists; raw interaction text and paired camera-view embeddings remain explicit gaps.",
-    "raw_128_overlay": "128-episode raw-feature baselines use staged sensor NPZ features. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
+    "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
+    "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+  },
+  "chart_design": {
+    "mode": "grouped_small_multiples",
+    "method_count": 9,
+    "reason": "The public release has nine methods and 180 scored records; small-multiple radar panels avoid a nine-polygon overlay while keeping every method visible.",
+    "groups": [
+      {
+        "id": "single_episode",
+        "title": "Single-episode sample",
+        "series_ids": [
+          "minimal",
+          "neural_mlp"
+        ]
+      },
+      {
+        "id": "metadata_128",
+        "title": "128-episode metadata/text",
+        "series_ids": [
+          "metadata128_simple",
+          "metadata128_neural_mlp"
+        ]
+      },
+      {
+        "id": "raw_128",
+        "title": "128-episode raw features",
+        "series_ids": [
+          "raw128_simple",
+          "raw128_neural_mlp"
+        ]
+      },
+      {
+        "id": "foundation_models",
+        "title": "Foundation-model probes",
+        "series_ids": [
+          "qwen3_omni_v6_lora",
+          "cosmos3_super_reasoner",
+          "cosmos3_nano_future_window"
+        ]
+      }
+    ],
+    "visual_radius_transform": "sqrt(normalized_score)",
+    "exact_value_source": "docs/data/task_method_20_result_matrix.json"
   },
   "series": [
     {
@@ -25,7 +68,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode simple heads over the public sample split.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -48,7 +91,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -71,7 +114,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "9 6",
       "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -95,7 +138,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "3 6",
       "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -119,7 +162,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "8 4",
       "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -143,7 +186,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "2 5",
       "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -167,7 +210,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
       "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -190,7 +233,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
       "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -213,7 +256,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "2 7",
       "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

docs/data/website_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:01:18+00:00",
+  "generated_at_utc": "2026-06-21T20:35:18+00:00",
   "docs_root": "docs",
   "site_base": "/ropedia-xperience-10m-task-suite/",
   "summary": {
@@ -80,8 +80,8 @@
       "name": "project_overview_precedes_progress_ledger",
       "status": "pass",
       "reason": "The project overview should appear before the deeper progress ledger.",
-      "overview_index": 136413,
-      "evidence_index": 187740
+      "overview_index": 136346,
+      "evidence_index": 187681
     },
     {
       "name": "project_status_links_json",
@@ -159,9 +159,9 @@
       "name": "evaluation_protocol_between_overview_and_progress",
       "status": "pass",
       "reason": "The evaluation protocol should appear before the deeper evidence ledger.",
-      "overview_index": 136413,
-      "protocol_index": 183928,
-      "evidence_index": 187740
+      "overview_index": 136346,
+      "protocol_index": 183869,
+      "evidence_index": 187681
     },
     {
       "name": "evaluation_protocol_links_json",
@@ -187,7 +187,7 @@
       "status": "pass",
       "reason": "The Suite anchor should show the task-suite map before the radar/results surface.",
       "first_marker_index": 468,
-      "second_marker_index": 1838
+      "second_marker_index": 2000
     },
     {
       "name": "raw_sample_stream_ledger_contains_seven_modalities",
@@ -315,7 +315,7 @@
     },
     {
       "path": "data/artifact_index.json",
-      "bytes": 124341,
+      "bytes": 124471,
       "top_level_type": "dict"
     },
     {
@@ -330,7 +330,7 @@
     },
     {
       "path": "data/episode128_task_model_radar.json",
-      "bytes": 185212,
+      "bytes": 186828,
       "top_level_type": "dict"
     },
     {
@@ -345,7 +345,7 @@
     },
     {
       "path": "data/figure_index.json",
-      "bytes": 19485,
+      "bytes": 19526,
       "top_level_type": "dict"
     },
     {
@@ -495,7 +495,7 @@
     },
     {
       "path": "data/single_episode_task_model_radar.json",
-      "bytes": 51327,
+      "bytes": 52256,
       "top_level_type": "dict"
     },
     {
@@ -515,7 +515,7 @@
     },
     {
       "path": "data/task_method_20_result_matrix.json",
-      "bytes": 128509,
+      "bytes": 128991,
       "top_level_type": "dict"
     },
     {
@@ -565,7 +565,7 @@
     },
     {
       "path": "data/unified_task_model_radar.json",
-      "bytes": 229035,
+      "bytes": 230938,
       "top_level_type": "dict"
     },
     {
@@ -610,7 +610,7 @@
     {
       "path": "assets/charts/episode128_task_model_radar.svg",
       "exists": true,
-      "bytes": 51915,
+      "bytes": 79370,
       "format": "SVG",
       "has_viewbox": true
     },
@@ -666,7 +666,7 @@
     {
       "path": "assets/charts/single_episode_task_model_radar.svg",
       "exists": true,
-      "bytes": 35232,
+      "bytes": 36930,
       "format": "SVG",
       "has_viewbox": true
     },
@@ -680,7 +680,7 @@
     {
       "path": "assets/charts/unified_task_model_radar.svg",
       "exists": true,
-      "bytes": 57938,
+      "bytes": 98527,
       "format": "SVG",
       "has_viewbox": true
     },

docs/index.html

@@ -4654,15 +4654,15 @@
       <div class="hero-radar-panel" aria-label="Unified 20-task radar comparison">
         <div class="hero-radar-top">
           <strong>home radar comparison</strong>
-          <span>two evidence lines / 180 scored records / 174 direct + 6 compact-proxy</span>
+          <span>4 grouped panels / 180 scored records / 174 direct + 6 compact-proxy</span>
         </div>
         <div class="hero-radar-layout">
           <a class="hero-radar-frame" href="#suite" aria-label="Open full unified 20-task model radar">
-            <img src="assets/charts/unified_task_model_radar.svg?v=xperience10m-20task-radar-v6" alt="Unified 20-task model radar with full task-name key, method legend, 20-record counts, score counts, and raw128 proxy notes">
+            <img src="assets/charts/unified_task_model_radar.svg?v=xperience10m-20task-radar-v7" alt="Unified 20-task grouped radar board with method-family panels, task key, score counts, and raw128 proxy notes">
           </a>
           <div class="hero-radar-copy">
-            <h2>Model comparison is split by evidence line.</h2>
-            <p>The full SVG names every task axis and keeps method records, source artifacts, and proxy notes attached to the same comparison view.</p>
+            <h2>Model comparison is grouped by method family.</h2>
+            <p>The full SVG names every task axis, separates the nine methods into readable panels, and keeps source artifacts plus proxy notes attached to the same comparison view.</p>
             <div class="hero-radar-stats" aria-label="Radar coverage summary">
               <div class="hero-radar-stat"><strong>180</strong><span>method-task records</span></div>
               <div class="hero-radar-stat"><strong>174</strong><span>direct scores</span></div>
@@ -4670,10 +4670,10 @@
               <div class="hero-radar-stat"><strong>34,269</strong><span>128ep windows</span></div>
             </div>
             <div class="hero-method-list" aria-label="Method families shown in the radar">
-              <div class="hero-method" style="--method-color:#67e8d1"><strong>Line 1: Minimal + Neural MLP</strong><span>Single public-sample episode; 40/40 direct task scores.</span></div>
-              <div class="hero-method" style="--method-color:#f59e0b"><strong>Line 2: metadata + raw baselines</strong><span>Same selected-128 split; all four baseline rows have 20 records, with proxy notes where direct raw targets are absent.</span></div>
-              <div class="hero-method" style="--method-color:#9bb8ff"><strong>Line 2: Qwen3-Omni v6 LoRA</strong><span>One trainable selected-128 model row; 20/20 direct scores from verified LoRA and task-specific probe artifacts.</span></div>
-              <div class="hero-method" style="--method-color:#d8f4a5"><strong>Line 2: Cosmos3 series</strong><span>Cosmos3-Super Reasoner and Cosmos3-Nano Future Window are separate selected-128 method rows; 40/40 direct scores.</span></div>
+              <div class="hero-method" style="--method-color:#67e8d1"><strong>Panel 1: Minimal + Neural MLP</strong><span>Single public-sample episode; 40/40 direct task scores.</span></div>
+              <div class="hero-method" style="--method-color:#ffd166"><strong>Panel 2: 128ep metadata/text</strong><span>Aligned JSONL and staged-target baselines; 40/40 scored with proxy flags retained.</span></div>
+              <div class="hero-method" style="--method-color:#22d3ee"><strong>Panel 3: 128ep raw features</strong><span>Sensor-block simple/NN heads; 40/40 scored with task 15/19 compact proxies marked.</span></div>
+              <div class="hero-method" style="--method-color:#9bb8ff"><strong>Panel 4: Qwen3 + Cosmos3</strong><span>Qwen3-Omni v6 LoRA, Cosmos3-Super, and Cosmos3-Nano; 60/60 scored from verified artifacts.</span></div>
             </div>
             <div class="hero-task-strip" aria-label="Radar task axis examples">
               <span>01 Action Recognition</span>
@@ -5065,7 +5065,7 @@
           <article class="split-radar-card">
             <h3>1-Episode 20-Task Radar</h3>
             <p>Minimal and Neural MLP baselines over the original public-sample episode, with 40/40 scored method-task records.</p>
-            <img src="assets/charts/single_episode_task_model_radar.svg?v=xperience10m-split-radar-v1" alt="Single-episode 20-task radar comparing Minimal and Neural MLP across all 20 scored task axes">
+            <img src="assets/charts/single_episode_task_model_radar.svg?v=xperience10m-split-radar-v2" alt="Single-episode 20-task radar comparing Minimal and Neural MLP across all 20 scored task axes">
             <div class="split-radar-links">
               <a href="assets/charts/single_episode_task_model_radar.svg">Open SVG</a>
               <a href="data/single_episode_task_model_radar.json">Open JSON</a>
@@ -5074,7 +5074,7 @@
           <article class="split-radar-card">
             <h3>128-Episode 20-Task Radar</h3>
             <p>Metadata, raw-feature, Qwen3-Omni, and Cosmos3 methods on the aligned 128-episode surface, with all 140 rows scored and proxy/evidence notes kept explicit.</p>
-            <img src="assets/charts/episode128_task_model_radar.svg?v=xperience10m-split-radar-v1" alt="128-episode 20-task radar comparing raw-feature baselines, metadata baselines, Qwen3-Omni, and Cosmos3 series with explicit score counts">
+            <img src="assets/charts/episode128_task_model_radar.svg?v=xperience10m-split-radar-v2" alt="128-episode grouped 20-task radar comparing metadata baselines, raw-feature baselines, Qwen3-Omni, and Cosmos3 series with explicit score counts">
             <div class="split-radar-links">
               <a href="assets/charts/episode128_task_model_radar.svg">Open SVG</a>
               <a href="data/episode128_task_model_radar.json">Open JSON</a>
@@ -5777,23 +5777,23 @@
         <div class="figure-brief">
           <article class="figure-brief-card">
             <h3>Unified plus split radars</h3>
-            <p>The unified radar keeps all 9 methods in one view. The split radars separate the 1-episode Minimal/NN baseline comparison from the 128-episode metadata/raw, Qwen3-Omni v6 LoRA, and Cosmos3-Super/Nano comparison.</p>
+            <p>The unified radar keeps all nine methods in one comparison board, but groups them into small-multiple panels so each method family can be read directly. The split radars separate the 1-episode Minimal/NN baseline comparison from the 128-episode metadata/raw, Qwen3-Omni v6 LoRA, and Cosmos3-Super/Nano comparison.</p>
           </article>
           <article class="figure-brief-card">
             <h3>Metric normalization</h3>
-            <p>Higher-is-better metrics are plotted directly on 0-1 axes. Lower-is-better metrics are converted to best/value within the task, while raw values, status reasons, sources, and the two raw128 compact proxy notes remain in the JSON mirrors.</p>
+            <p>Higher-is-better metrics are normalized to 0-1; lower-is-better metrics are converted to best/value within the task. The SVG uses sqrt(normalized score) only for visual radius, while raw values, linear normalized scores, status reasons, sources, and compact proxy notes remain in the JSON mirrors.</p>
           </article>
           <article class="figure-brief-card">
             <h3>Score/proxy audit</h3>
             <p>The matrix has 180/180 scored method-task records: 174 direct scores and 6 compact-proxy scores. The audit records the source artifact, metric key, and proxy reason for each marked cell.</p>
           </article>
         </div>
-        <img class="chart radar-chart unified-radar-chart" src="assets/charts/unified_task_model_radar.svg?v=xperience10m-20task-radar-v6" alt="Unified 20-task radar comparing Minimal, Neural MLP, 128-episode metadata/raw baselines, Qwen3-Omni, and Cosmos3 with task names, method details, 20-record counts, score counts, and proxy notes">
+        <img class="chart radar-chart unified-radar-chart" src="assets/charts/unified_task_model_radar.svg?v=xperience10m-20task-radar-v7" alt="Unified grouped 20-task radar comparing Minimal, Neural MLP, 128-episode metadata/raw baselines, Qwen3-Omni, and Cosmos3 with task names, method details, 20-record counts, score counts, and proxy notes">
         <div class="split-radar-grid" aria-label="Split 20-task radar comparisons">
           <article class="split-radar-card">
             <h3>1-Episode 20-Task Radar</h3>
-            <p>Minimal and Neural MLP are both scored on all 20 public-sample task contracts, shown as two filled polygons without 128-episode overlays.</p>
-            <img src="assets/charts/single_episode_task_model_radar.svg?v=xperience10m-split-radar-v1" alt="Single-episode 20-task radar comparing Minimal and Neural MLP across all 20 scored task axes">
+            <p>Minimal and Neural MLP are both scored on all 20 public-sample task contracts in one enlarged panel without 128-episode methods competing for attention.</p>
+            <img src="assets/charts/single_episode_task_model_radar.svg?v=xperience10m-split-radar-v2" alt="Single-episode 20-task radar comparing Minimal and Neural MLP across all 20 scored task axes">
             <div class="split-radar-links">
               <a href="assets/charts/single_episode_task_model_radar.svg">Open SVG</a>
               <a href="data/single_episode_task_model_radar.json">Open JSON</a>
@@ -5801,8 +5801,8 @@
           </article>
           <article class="split-radar-card">
             <h3>128-Episode 20-Task Radar</h3>
-            <p>Seven aligned 128-episode methods cover all 20 axes: metadata simple/NN, raw-feature simple/NN, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano. Proxy axes stay labeled in the JSON.</p>
-            <img src="assets/charts/episode128_task_model_radar.svg?v=xperience10m-split-radar-v1" alt="128-episode 20-task radar comparing raw-feature baselines, metadata baselines, Qwen3-Omni, and Cosmos3 series with explicit score counts">
+            <p>Seven aligned 128-episode methods cover all 20 axes across metadata/text, raw-feature, and foundation-model panels. Proxy axes stay labeled in the SVG and JSON.</p>
+            <img src="assets/charts/episode128_task_model_radar.svg?v=xperience10m-split-radar-v2" alt="128-episode grouped 20-task radar comparing raw-feature baselines, metadata baselines, Qwen3-Omni, and Cosmos3 series with explicit score counts">
             <div class="split-radar-links">
               <a href="assets/charts/episode128_task_model_radar.svg">Open SVG</a>
               <a href="data/episode128_task_model_radar.json">Open JSON</a>

index.html

@@ -4654,15 +4654,15 @@
       <div class="hero-radar-panel" aria-label="Unified 20-task radar comparison">
         <div class="hero-radar-top">
           <strong>home radar comparison</strong>
-          <span>two evidence lines / 180 scored records / 174 direct + 6 compact-proxy</span>
+          <span>4 grouped panels / 180 scored records / 174 direct + 6 compact-proxy</span>
         </div>
         <div class="hero-radar-layout">
           <a class="hero-radar-frame" href="#suite" aria-label="Open full unified 20-task model radar">
-            <img src="assets/charts/unified_task_model_radar.svg?v=xperience10m-20task-radar-v6" alt="Unified 20-task model radar with full task-name key, method legend, 20-record counts, score counts, and raw128 proxy notes">
+            <img src="assets/charts/unified_task_model_radar.svg?v=xperience10m-20task-radar-v7" alt="Unified 20-task grouped radar board with method-family panels, task key, score counts, and raw128 proxy notes">
           </a>
           <div class="hero-radar-copy">
-            <h2>Model comparison is split by evidence line.</h2>
-            <p>The full SVG names every task axis and keeps method records, source artifacts, and proxy notes attached to the same comparison view.</p>
+            <h2>Model comparison is grouped by method family.</h2>
+            <p>The full SVG names every task axis, separates the nine methods into readable panels, and keeps source artifacts plus proxy notes attached to the same comparison view.</p>
             <div class="hero-radar-stats" aria-label="Radar coverage summary">
               <div class="hero-radar-stat"><strong>180</strong><span>method-task records</span></div>
               <div class="hero-radar-stat"><strong>174</strong><span>direct scores</span></div>
@@ -4670,10 +4670,10 @@
               <div class="hero-radar-stat"><strong>34,269</strong><span>128ep windows</span></div>
             </div>
             <div class="hero-method-list" aria-label="Method families shown in the radar">
-              <div class="hero-method" style="--method-color:#67e8d1"><strong>Line 1: Minimal + Neural MLP</strong><span>Single public-sample episode; 40/40 direct task scores.</span></div>
-              <div class="hero-method" style="--method-color:#f59e0b"><strong>Line 2: metadata + raw baselines</strong><span>Same selected-128 split; all four baseline rows have 20 records, with proxy notes where direct raw targets are absent.</span></div>
-              <div class="hero-method" style="--method-color:#9bb8ff"><strong>Line 2: Qwen3-Omni v6 LoRA</strong><span>One trainable selected-128 model row; 20/20 direct scores from verified LoRA and task-specific probe artifacts.</span></div>
-              <div class="hero-method" style="--method-color:#d8f4a5"><strong>Line 2: Cosmos3 series</strong><span>Cosmos3-Super Reasoner and Cosmos3-Nano Future Window are separate selected-128 method rows; 40/40 direct scores.</span></div>
+              <div class="hero-method" style="--method-color:#67e8d1"><strong>Panel 1: Minimal + Neural MLP</strong><span>Single public-sample episode; 40/40 direct task scores.</span></div>
+              <div class="hero-method" style="--method-color:#ffd166"><strong>Panel 2: 128ep metadata/text</strong><span>Aligned JSONL and staged-target baselines; 40/40 scored with proxy flags retained.</span></div>
+              <div class="hero-method" style="--method-color:#22d3ee"><strong>Panel 3: 128ep raw features</strong><span>Sensor-block simple/NN heads; 40/40 scored with task 15/19 compact proxies marked.</span></div>
+              <div class="hero-method" style="--method-color:#9bb8ff"><strong>Panel 4: Qwen3 + Cosmos3</strong><span>Qwen3-Omni v6 LoRA, Cosmos3-Super, and Cosmos3-Nano; 60/60 scored from verified artifacts.</span></div>
             </div>
             <div class="hero-task-strip" aria-label="Radar task axis examples">
               <span>01 Action Recognition</span>
@@ -5065,7 +5065,7 @@
           <article class="split-radar-card">
             <h3>1-Episode 20-Task Radar</h3>
             <p>Minimal and Neural MLP baselines over the original public-sample episode, with 40/40 scored method-task records.</p>
-            <img src="assets/charts/single_episode_task_model_radar.svg?v=xperience10m-split-radar-v1" alt="Single-episode 20-task radar comparing Minimal and Neural MLP across all 20 scored task axes">
+            <img src="assets/charts/single_episode_task_model_radar.svg?v=xperience10m-split-radar-v2" alt="Single-episode 20-task radar comparing Minimal and Neural MLP across all 20 scored task axes">
             <div class="split-radar-links">
               <a href="assets/charts/single_episode_task_model_radar.svg">Open SVG</a>
               <a href="data/single_episode_task_model_radar.json">Open JSON</a>
@@ -5074,7 +5074,7 @@
           <article class="split-radar-card">
             <h3>128-Episode 20-Task Radar</h3>
             <p>Metadata, raw-feature, Qwen3-Omni, and Cosmos3 methods on the aligned 128-episode surface, with all 140 rows scored and proxy/evidence notes kept explicit.</p>
-            <img src="assets/charts/episode128_task_model_radar.svg?v=xperience10m-split-radar-v1" alt="128-episode 20-task radar comparing raw-feature baselines, metadata baselines, Qwen3-Omni, and Cosmos3 series with explicit score counts">
+            <img src="assets/charts/episode128_task_model_radar.svg?v=xperience10m-split-radar-v2" alt="128-episode grouped 20-task radar comparing metadata baselines, raw-feature baselines, Qwen3-Omni, and Cosmos3 series with explicit score counts">
             <div class="split-radar-links">
               <a href="assets/charts/episode128_task_model_radar.svg">Open SVG</a>
               <a href="data/episode128_task_model_radar.json">Open JSON</a>
@@ -5777,23 +5777,23 @@
         <div class="figure-brief">
           <article class="figure-brief-card">
             <h3>Unified plus split radars</h3>
-            <p>The unified radar keeps all 9 methods in one view. The split radars separate the 1-episode Minimal/NN baseline comparison from the 128-episode metadata/raw, Qwen3-Omni v6 LoRA, and Cosmos3-Super/Nano comparison.</p>
+            <p>The unified radar keeps all nine methods in one comparison board, but groups them into small-multiple panels so each method family can be read directly. The split radars separate the 1-episode Minimal/NN baseline comparison from the 128-episode metadata/raw, Qwen3-Omni v6 LoRA, and Cosmos3-Super/Nano comparison.</p>
           </article>
           <article class="figure-brief-card">
             <h3>Metric normalization</h3>
-            <p>Higher-is-better metrics are plotted directly on 0-1 axes. Lower-is-better metrics are converted to best/value within the task, while raw values, status reasons, sources, and the two raw128 compact proxy notes remain in the JSON mirrors.</p>
+            <p>Higher-is-better metrics are normalized to 0-1; lower-is-better metrics are converted to best/value within the task. The SVG uses sqrt(normalized score) only for visual radius, while raw values, linear normalized scores, status reasons, sources, and compact proxy notes remain in the JSON mirrors.</p>
           </article>
           <article class="figure-brief-card">
             <h3>Score/proxy audit</h3>
             <p>The matrix has 180/180 scored method-task records: 174 direct scores and 6 compact-proxy scores. The audit records the source artifact, metric key, and proxy reason for each marked cell.</p>
           </article>
         </div>
-        <img class="chart radar-chart unified-radar-chart" src="assets/charts/unified_task_model_radar.svg?v=xperience10m-20task-radar-v6" alt="Unified 20-task radar comparing Minimal, Neural MLP, 128-episode metadata/raw baselines, Qwen3-Omni, and Cosmos3 with task names, method details, 20-record counts, score counts, and proxy notes">
+        <img class="chart radar-chart unified-radar-chart" src="assets/charts/unified_task_model_radar.svg?v=xperience10m-20task-radar-v7" alt="Unified grouped 20-task radar comparing Minimal, Neural MLP, 128-episode metadata/raw baselines, Qwen3-Omni, and Cosmos3 with task names, method details, 20-record counts, score counts, and proxy notes">
         <div class="split-radar-grid" aria-label="Split 20-task radar comparisons">
           <article class="split-radar-card">
             <h3>1-Episode 20-Task Radar</h3>
-            <p>Minimal and Neural MLP are both scored on all 20 public-sample task contracts, shown as two filled polygons without 128-episode overlays.</p>
-            <img src="assets/charts/single_episode_task_model_radar.svg?v=xperience10m-split-radar-v1" alt="Single-episode 20-task radar comparing Minimal and Neural MLP across all 20 scored task axes">
+            <p>Minimal and Neural MLP are both scored on all 20 public-sample task contracts in one enlarged panel without 128-episode methods competing for attention.</p>
+            <img src="assets/charts/single_episode_task_model_radar.svg?v=xperience10m-split-radar-v2" alt="Single-episode 20-task radar comparing Minimal and Neural MLP across all 20 scored task axes">
             <div class="split-radar-links">
               <a href="assets/charts/single_episode_task_model_radar.svg">Open SVG</a>
               <a href="data/single_episode_task_model_radar.json">Open JSON</a>
@@ -5801,8 +5801,8 @@
           </article>
           <article class="split-radar-card">
             <h3>128-Episode 20-Task Radar</h3>
-            <p>Seven aligned 128-episode methods cover all 20 axes: metadata simple/NN, raw-feature simple/NN, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano. Proxy axes stay labeled in the JSON.</p>
-            <img src="assets/charts/episode128_task_model_radar.svg?v=xperience10m-split-radar-v1" alt="128-episode 20-task radar comparing raw-feature baselines, metadata baselines, Qwen3-Omni, and Cosmos3 series with explicit score counts">
+            <p>Seven aligned 128-episode methods cover all 20 axes across metadata/text, raw-feature, and foundation-model panels. Proxy axes stay labeled in the SVG and JSON.</p>
+            <img src="assets/charts/episode128_task_model_radar.svg?v=xperience10m-split-radar-v2" alt="128-episode grouped 20-task radar comparing raw-feature baselines, metadata baselines, Qwen3-Omni, and Cosmos3 series with explicit score counts">
             <div class="split-radar-links">
               <a href="assets/charts/episode128_task_model_radar.svg">Open SVG</a>
               <a href="data/episode128_task_model_radar.json">Open JSON</a>

metrics/artifact_index.json

@@ -1,6 +1,6 @@
 {
   "title": "Ropedia Xperience-10M Task Suite Artifact Index",
-  "generated_at_utc": "2026-06-21T15:19:00+00:00",
+  "generated_at_utc": "2026-06-21T20:35:18+00:00",
   "status": "pass",
   "artifact_count": 228,
   "missing": [],
@@ -92,8 +92,8 @@
       "surface": "repo_hf",
       "shows": "Defines terminology that can be confused across data scope, task metrics, model branches, and public mirrors.",
       "exists": true,
-      "bytes": 10220,
-      "sha256": "c3723a3dfaf902f4bc2527b78d11057ab8ba01c6b9715fa873c7dd819deddf81"
+      "bytes": 10857,
+      "sha256": "b9b8f8695b6c211e849073e1634057f158877a61161eca05b1266769158ee83e"
     },
     {
       "id": "glossary_json",
@@ -103,8 +103,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable terminology layer for the website, artifact dataset, model mirror, and public QA checks.",
       "exists": true,
-      "bytes": 17380,
-      "sha256": "3ba746413eb4a7d2646333e3746e0b3f4039db61d03c159d2d059fecfe4b51ed"
+      "bytes": 18754,
+      "sha256": "b1dc42e1f42a7c19bb4b2ebd32a0862df28bec671eaa849b09a97f103675e9eb"
     },
     {
       "id": "research_roadmap",
@@ -158,8 +158,8 @@
       "surface": "repo_hf",
       "shows": "Frames spatial intelligence, human-video world modeling, and vision-language-action as three pipeline tracks with explicit inputs, outputs, maturity, and next evidence gates.",
       "exists": true,
-      "bytes": 8008,
-      "sha256": "abd179631f1d204328fa5a2e018207eceeb7d46be12b7dab2826e70dfde97130"
+      "bytes": 11609,
+      "sha256": "69d4d8781015c807c58a720b3bf967ee872540a2fe2b7e7973105946c5a1cf11"
     },
     {
       "id": "three_foundation_pipelines_json",
@@ -169,8 +169,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable pipeline-track contract for the website and Hugging Face mirrors.",
       "exists": true,
-      "bytes": 10312,
-      "sha256": "9eb30d098f1b3787255a5506e4299f2cd4904ef989f2eaeaa2e5f77519c17378"
+      "bytes": 14465,
+      "sha256": "c8c9b7a9ee8d3ecfe8662cf0336a7ca2ade6d670c5567d2a50dfb67c7241defd"
     },
     {
       "id": "spatial_intelligence_slide_diagram",
@@ -632,7 +632,7 @@
       "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
       "exists": true,
       "bytes": 4432,
-      "sha256": "5ab2ea4bfefe9f5bc7854f02b2e1e2b5206766a54447647191828da1a1a2077c"
+      "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
     },
     {
       "id": "source_alignment_validator",
@@ -653,8 +653,8 @@
       "surface": "repo_hf",
       "shows": "Publishes prepared Space, artifact dataset, and model bundles, including an explicit model-binary upload batch.",
       "exists": true,
-      "bytes": 25115,
-      "sha256": "31866958ffaa3954f1bc4f920fbf80d5b41fd95228be50989dadb6e8cbe619e3"
+      "bytes": 29935,
+      "sha256": "89ed1b25784cd42f19f2e4731eaa52e8655e8ed06cc2a12b6a2c0add027c5fc0"
     },
     {
       "id": "github_package_dockerfile",
@@ -697,8 +697,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable protocol generated from committed task metrics for website and HF mirrors.",
       "exists": true,
-      "bytes": 24047,
-      "sha256": "d8f61b646a2f3f1e0af901dbdaff310ebfeea90622c93a34b9e35f34be98b896"
+      "bytes": 24267,
+      "sha256": "83289b52e0193fa86d63fac7dd8af98d0612199b1e1a5f5ed37014baa9168656"
     },
     {
       "id": "evaluation_protocol_builder",
@@ -708,8 +708,8 @@
       "surface": "repo_hf",
       "shows": "Regenerates the protocol from committed summary metrics and task artifacts.",
       "exists": true,
-      "bytes": 19825,
-      "sha256": "aa9de1582f8fa79c1850e10e69fb125c0e3c1add433c7ebedc104c2efb42272e"
+      "bytes": 19845,
+      "sha256": "b5d888fd67ba6b8150b24960aa0858db50f16a5c7b59a8ce274401e384f0a2a3"
     },
     {
       "id": "task_suite_20",
@@ -730,8 +730,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable unified 20-task index for the website, Hugging Face mirrors, and live verification.",
       "exists": true,
-      "bytes": 34585,
-      "sha256": "75145285cf71bc3bb9a10377a1921b60e85c4546dc8b858102b3c26e94c11a01"
+      "bytes": 34805,
+      "sha256": "5d7a3b5b57e64980291b3ce6a8741b0b822e94bd447ca95519d1da7040923476"
     },
     {
       "id": "task_suite_20_builder",
@@ -741,8 +741,8 @@
       "surface": "repo_hf",
       "shows": "Regenerates the unified 20-task JSON and Markdown from the public-sample metrics plus the historical provenance result bundle.",
       "exists": true,
-      "bytes": 12157,
-      "sha256": "157265b5c025f279ce1eb56c52dd720ce0969b8426d5887030bfa179a3b565e0"
+      "bytes": 12129,
+      "sha256": "4c2550c657bfa5bc37e21e78e7e27dd70daa3b178c8ffb3191e52f835221713a"
     },
     {
       "id": "unified_task_model_radar_json",
@@ -750,10 +750,10 @@
       "path": "docs/data/unified_task_model_radar.json",
       "kind": "website_data",
       "surface": "website_hf",
-      "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3-Omni/Cosmos3 overlay mappings, method-card caveats, proxy flags, and source artifacts.",
+      "shows": "Stores normalized 20-axis radar values, raw task metrics, grouped chart-design metadata, Qwen3-Omni/Cosmos3 source mappings, method-card caveats, proxy flags, and source artifacts.",
       "exists": true,
-      "bytes": 228815,
-      "sha256": "862376178e8b0d01b536f49a18b7934a373494f8b36080790f616438ec0e035e"
+      "bytes": 230938,
+      "sha256": "bd7b8fd8a169273c5cec2beab050a583307dcc64e5e3fefcd690484b4a0754bc"
     },
     {
       "id": "single_episode_task_model_radar_json",
@@ -763,8 +763,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
       "exists": true,
-      "bytes": 51107,
-      "sha256": "5f2ebb41e8488446ea5c5cd2cb75bbedce688433feffe1412288de56b133bd5c"
+      "bytes": 52256,
+      "sha256": "f282dc0c4c654fe6f2cd646612fd0942d267dec60c6143cc36688edbc27c13da"
     },
     {
       "id": "episode128_task_model_radar_json",
@@ -774,8 +774,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines, Qwen3-Omni v6, Cosmos3-Super, and Cosmos3-Nano, now complete at 140/140 scored rows with proxy notes retained.",
       "exists": true,
-      "bytes": 184992,
-      "sha256": "385704db90443d74903f365e90b27538020f5574c96f296bbf63173f488a645d"
+      "bytes": 186828,
+      "sha256": "f904cf9eb3160a50e4469989e44557e77d710e459f812ba7b194d0ed8d9746bd"
     },
     {
       "id": "task_method_20_result_matrix_json",
@@ -785,8 +785,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and the current release is complete at 180/180 scored rows.",
       "exists": true,
-      "bytes": 128509,
-      "sha256": "96082daa33771963ac40b7d719df00a76ec443508a3d3101cb6dd82d87965729"
+      "bytes": 128991,
+      "sha256": "bacb549e64b6d1936b55fe7593cfbaeb1dbf5bfe824c8507ea75e493230212fe"
     },
     {
       "id": "task_method_20_result_matrix",
@@ -796,8 +796,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing table that separates 20 records per method, direct numeric scores, documented compact-proxy scores, and source artifacts.",
       "exists": true,
-      "bytes": 3563,
-      "sha256": "84b21bd3359e6149b952a9b3b6991f7ba8ff412390a92983bd6d59f212d58316"
+      "bytes": 14862,
+      "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
     },
     {
       "id": "task_method_20_gap_audit_json",
@@ -808,7 +808,7 @@
       "shows": "Machine-readable 180-record completion ledger with numeric scores, proxy flags, explicit status reasons, and source artifacts.",
       "exists": true,
       "bytes": 8500,
-      "sha256": "5743354519dfae924d973ffca90a5d1ef4b0c316cf201b3ac443f6b5d4600de5"
+      "sha256": "4f5cc7a29fe030a9fd5b97893ac67454ebc6287f5942aeedb2bfca71c411332d"
     },
     {
       "id": "task_method_20_gap_audit",
@@ -819,7 +819,7 @@
       "shows": "Reader-facing ledger confirming 180/180 scored method-task cells and listing the six compact-proxy records separately.",
       "exists": true,
       "bytes": 3417,
-      "sha256": "01f47c74db965887e55f17b674e1617e396dd01a51fdc7bf9a9c7612f5596b2c"
+      "sha256": "b094732dd98c904ea0ab30e741576a3d5eeb8ca07e7a494e459b11e31320ae4d"
     },
     {
       "id": "task_method_20_source_audit_json",
@@ -830,7 +830,7 @@
       "shows": "Machine-readable check that scored JSON-backed matrix cells match their declared metric source values.",
       "exists": true,
       "bytes": 561,
-      "sha256": "bb50000bb681f1ed12c4089bd3541f14b8e121ea5a1fe06e1a6a559cb8960e0b"
+      "sha256": "1bc6bb15ab45e73ada4d3c2d1ec326cffd9c6bc6d6d791c7468b3ed16881a463"
     },
     {
       "id": "task_method_20_source_audit",
@@ -841,7 +841,7 @@
       "shows": "Reader-facing source-value audit for the 180-result matrix.",
       "exists": true,
       "bytes": 447,
-      "sha256": "1a0583629368cee3abadc49d4a0220dead924326a04e82b3a22a9fc6d6b0d252"
+      "sha256": "7f5e80d6dcd66be1c6b2c63144adb64d0cdad0008884ebd8f015388545e4b914"
     },
     {
       "id": "two_evidence_line_map_chart",
@@ -860,10 +860,10 @@
       "path": "docs/assets/charts/unified_task_model_radar.svg",
       "kind": "generated_figure",
       "surface": "website_hf",
-      "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3-Omni and Cosmos3 task-aligned overlays.",
+      "shows": "Groups all nine methods into small-multiple 20-task radar panels so single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows remain readable.",
       "exists": true,
-      "bytes": 57938,
-      "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+      "bytes": 98527,
+      "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
     },
     {
       "id": "single_episode_task_model_radar_chart",
@@ -871,10 +871,10 @@
       "path": "docs/assets/charts/single_episode_task_model_radar.svg",
       "kind": "generated_figure",
       "surface": "website_hf",
-      "shows": "Separates the one-episode Minimal and Neural MLP 20/20 scored baselines into a clean two-polygon radar.",
+      "shows": "Shows the one-episode Minimal and Neural MLP 20/20 scored baselines in one enlarged radar panel with local legend and task key.",
       "exists": true,
-      "bytes": 35232,
-      "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+      "bytes": 36930,
+      "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
     },
     {
       "id": "episode128_task_model_radar_chart",
@@ -882,10 +882,10 @@
       "path": "docs/assets/charts/episode128_task_model_radar.svg",
       "kind": "generated_figure",
       "surface": "website_hf",
-      "shows": "Separates the selected 128-episode methods: raw-feature simple/NN as complete 20/20 scored polygons plus metadata, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano task-aligned overlays.",
+      "shows": "Separates selected 128-episode methods into metadata/text, raw-feature, and foundation-model radar panels with all 140 result rows scored and proxy notes retained.",
       "exists": true,
-      "bytes": 51915,
-      "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+      "bytes": 79370,
+      "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
     },
     {
       "id": "unified_task_model_radar_builder",
@@ -893,10 +893,10 @@
       "path": "scripts/build_unified_task_model_radar.py",
       "kind": "visualization_builder",
       "surface": "repo_hf",
-      "shows": "Regenerates the direction-aware radar chart and machine-readable metric overlay JSON.",
+      "shows": "Regenerates grouped 20-task radar charts plus machine-readable metric, source, chart-design, and proxy metadata.",
       "exists": true,
-      "bytes": 68610,
-      "sha256": "96bc2df0de5a9e512d69961ddb13ea87b26ef01f1f943f5a78a6dc373400949d"
+      "bytes": 79396,
+      "sha256": "78949d7030cf6995edbb1d46a35692c7fe835d102df619cdf8c9d8ea9c5318e2"
     },
     {
       "id": "task_method_20_gap_audit_builder",
@@ -1093,8 +1093,8 @@
       "surface": "repo_hf",
       "shows": "Catalogs public figures, charts, modality thumbnails, dimensions, hashes, roles, and source scripts.",
       "exists": true,
-      "bytes": 7027,
-      "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+      "bytes": 7068,
+      "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
     },
     {
       "id": "figure_index_json",
@@ -1104,8 +1104,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable visual asset index for website and Hugging Face mirrors.",
       "exists": true,
-      "bytes": 19485,
-      "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+      "bytes": 19526,
+      "sha256": "601acd715891bb148b0a1706573a2fdb015ca3c5967f02a169577b483b0dcd43"
     },
     {
       "id": "figure_index_builder",
@@ -1115,8 +1115,8 @@
       "surface": "repo_hf",
       "shows": "Regenerates visual-asset hashes, dimensions, and source-script provenance.",
       "exists": true,
-      "bytes": 16845,
-      "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+      "bytes": 16886,
+      "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
     },
     {
       "id": "brand_assets_json",
@@ -1182,7 +1182,7 @@
       "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
       "exists": true,
       "bytes": 8640,
-      "sha256": "6e54f6828b8fef97e963a9a56bccc91162b8a632f6897743095e32407fa0db98"
+      "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
     },
     {
       "id": "public_surface_qa",
@@ -1226,7 +1226,7 @@
       "volatile": true,
       "shows": "Machine-readable report for SEO/social metadata, accessible tab semantics, public links, project links, and clear project presentation.",
       "exists": true,
-      "bytes": 7691,
+      "bytes": 7693,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1318,8 +1318,8 @@
       "surface": "repo",
       "shows": "Fetches the published GitHub/HF URLs and compares live hashes and public-card markers against the release assets.",
       "exists": true,
-      "bytes": 69151,
-      "sha256": "c4af8644d50dafe7d4249dd7c5b36bb19e996628ff6d8436fbb6e027da526c1f"
+      "bytes": 69123,
+      "sha256": "a96d0a95ea1da54fb8b6a95b2c91d4a067eef8358d825c44d919e66d78ecb8f7"
     },
     {
       "id": "reproducibility_contract",
@@ -1351,8 +1351,8 @@
       "surface": "repo_hf",
       "shows": "Generates the selective artifact catalog from local files.",
       "exists": true,
-      "bytes": 68279,
-      "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+      "bytes": 68407,
+      "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
     },
     {
       "id": "publication_audit",
@@ -1363,7 +1363,7 @@
       "volatile": true,
       "shows": "Confirms public bundles exclude raw data, caches, heavy archives, and credential text.",
       "exists": true,
-      "bytes": 10939,
+      "bytes": 10940,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1387,7 +1387,7 @@
       "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": 1420743,
+      "bytes": 1420751,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1399,7 +1399,7 @@
       "volatile": true,
       "shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
       "exists": true,
-      "bytes": 20760,
+      "bytes": 20178,
       "hash_policy": "existence_and_size_only"
     },
     {

metrics/episode128_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "128-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+00:00",
   "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3-Omni v6, Cosmos3-Super, and Cosmos3-Nano diagnostics. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.",
   "task_count": 20,
   "method_count": 7,
@@ -11,10 +11,45 @@
     "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",
     "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
+    "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
     "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
-    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 points are plotted only on task-aligned axes. Scoreless records mean the public result does not evaluate that task contract.",
-    "metadata_128_overlay": "128-episode aligned baselines have 20 records. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists; raw interaction text and paired camera-view embeddings remain explicit gaps.",
-    "raw_128_overlay": "128-episode raw-feature baselines use staged sensor NPZ features. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
+    "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
+    "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+  },
+  "chart_design": {
+    "mode": "grouped_small_multiples",
+    "method_count": 7,
+    "reason": "This split view has 7 methods and 140 method-task records; grouped radar panels keep related methods readable while retaining the unified source matrix.",
+    "groups": [
+      {
+        "id": "metadata_128",
+        "title": "128-episode metadata/text",
+        "series_ids": [
+          "metadata128_simple",
+          "metadata128_neural_mlp"
+        ]
+      },
+      {
+        "id": "raw_128",
+        "title": "128-episode raw features",
+        "series_ids": [
+          "raw128_simple",
+          "raw128_neural_mlp"
+        ]
+      },
+      {
+        "id": "foundation_models",
+        "title": "Foundation-model probes",
+        "series_ids": [
+          "qwen3_omni_v6_lora",
+          "cosmos3_super_reasoner",
+          "cosmos3_nano_future_window"
+        ]
+      }
+    ],
+    "visual_radius_transform": "sqrt(normalized_score)",
+    "exact_value_source": "docs/data/task_method_20_result_matrix.json"
   },
   "source_unified_radar": "docs/data/unified_task_model_radar.json",
   "source_result_matrix": "docs/data/task_method_20_result_matrix.json",
@@ -28,7 +63,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "9 6",
       "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -52,7 +87,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "3 6",
       "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -76,7 +111,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "8 4",
       "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -100,7 +135,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "2 5",
       "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -124,7 +159,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
       "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -147,7 +182,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
       "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -170,7 +205,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "2 7",
       "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

metrics/figure_index.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Figure Index",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:19:00+00:00",
+  "generated_at_utc": "2026-06-21T20:35:17+00:00",
   "scope": "Public figures, diagrams, charts, and derived modality thumbnails. Raw Xperience-10M videos, annotations, RRD files, and Qwen weights are excluded.",
   "figure_count": 29,
   "figures": [
@@ -406,17 +406,17 @@
       "id": "unified_task_model_radar",
       "title": "Unified 20-task model radar",
       "path": "docs/assets/charts/unified_task_model_radar.svg",
-      "role": "Twenty-axis direction-aware comparison of minimal and neural MLP baselines, with 128-episode metadata, Qwen3, and Cosmos task-aligned overlay points and branch notes.",
+      "role": "Grouped small-multiple 20-task radar board for all nine methods, separating single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows while preserving task keys and proxy notes.",
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 57938,
-      "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8",
+      "bytes": 98527,
+      "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },
@@ -428,13 +428,13 @@
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 35232,
-      "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e",
+      "bytes": 36930,
+      "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },
@@ -442,17 +442,17 @@
       "id": "episode128_task_model_radar",
       "title": "128-episode 20-task model radar",
       "path": "docs/assets/charts/episode128_task_model_radar.svg",
-      "role": "Twenty-axis split radar for selected 128-episode methods: raw-feature simple/NN as complete scored polygons plus metadata, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano task-aligned overlays.",
+      "role": "Grouped 20-task radar for selected 128-episode methods: metadata/text baselines, raw-feature simple/NN, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano with local legends and proxy notes.",
       "source_script": "scripts/build_unified_task_model_radar.py",
       "surface": "website unified task section, README, HF mirrors",
       "exists": true,
-      "bytes": 51915,
-      "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4",
+      "bytes": 79370,
+      "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9",
       "dimensions": {
         "format": "SVG",
         "width": 2400,
-        "height": 1840,
-        "view_box": "0 0 2400 1840"
+        "height": 1900,
+        "view_box": "0 0 2400 1900"
       },
       "source_script_exists": true
     },

metrics/mirror_parity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:00:18+00:00",
+  "generated_at_utc": "2026-06-21T20:33:57+00:00",
   "hf_root": "hf_publish",
   "summary": {
     "group_count": 1258,
@@ -138,45 +138,45 @@
       "local": {
         "path": "repo:docs/data/artifact_index.json",
         "exists": true,
-        "bytes": 124341,
-        "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+        "bytes": 124471,
+        "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model_data": {
           "path": "hf_model:data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         },
         "hf_model": {
           "path": "hf_model:metrics/artifact_index.json",
           "exists": true,
-          "bytes": 124341,
-          "sha256": "d2887200f777fa80235644383d26cd3a171c313d9c4641e06974fb705f02ee5d"
+          "bytes": 124471,
+          "sha256": "8e9954b1de5bbd935a1ed0c6753f737d9a2a325c0bd85377087751ce198afeeb"
         }
       },
       "failures": []
@@ -334,45 +334,45 @@
       "local": {
         "path": "repo:docs/data/figure_index.json",
         "exists": true,
-        "bytes": 19485,
-        "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+        "bytes": 19526,
+        "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model_data": {
           "path": "hf_model:data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         },
         "hf_model": {
           "path": "hf_model:metrics/figure_index.json",
           "exists": true,
-          "bytes": 19485,
-          "sha256": "4f225bf08f00fbe843999d6bd2b3d5f5d6c17f2ff67e1f6a85eee9094c6bb6a3"
+          "bytes": 19526,
+          "sha256": "2216a4c718a2ad7aba2a6f3f30b2d699c77dea6a867219df40f2e7a83a467eb4"
         }
       },
       "failures": []
@@ -972,44 +972,44 @@
         "path": "repo:docs/data/publication_audit.json",
         "exists": true,
         "bytes": 10940,
-        "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+        "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model_data": {
           "path": "hf_model:data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         },
         "hf_model": {
           "path": "hf_model:metrics/publication_audit.json",
           "exists": true,
           "bytes": 10940,
-          "sha256": "656414245ff90b4f44a303ae2e848d5e893a8a861f1e4102d19a0dd979012997"
+          "sha256": "f5a4c25846e1a8d730f4dc540c1c4fb56bd204c7de3d426b7759e72529009a06"
         }
       },
       "failures": []
@@ -1021,44 +1021,44 @@
         "path": "repo:docs/data/public_surface_qa.json",
         "exists": true,
         "bytes": 7693,
-        "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+        "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model_data": {
           "path": "hf_model:data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         },
         "hf_model": {
           "path": "hf_model:metrics/public_surface_qa.json",
           "exists": true,
           "bytes": 7693,
-          "sha256": "7dc38f37df3efac5c7ce1213267dd7693515df5806be778138ea5f8de70b0111"
+          "sha256": "c3c9cab63c92026e5cf5265d5113d0bc42beec3664a71880c8471cc3305a8b04"
         }
       },
       "failures": []
@@ -1217,44 +1217,44 @@
         "path": "repo:docs/data/quality_gates.json",
         "exists": true,
         "bytes": 8640,
-        "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+        "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model_data": {
           "path": "hf_model:data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         },
         "hf_model": {
           "path": "hf_model:metrics/quality_gates.json",
           "exists": true,
           "bytes": 8640,
-          "sha256": "271e4f6363b8e3738274c0be42b403ae7f449effe87e34daec6477e048194ff0"
+          "sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
         }
       },
       "failures": []
@@ -1658,44 +1658,44 @@
         "path": "repo:docs/data/scope_claims_audit.json",
         "exists": true,
         "bytes": 21313,
-        "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+        "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model_data": {
           "path": "hf_model:data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         },
         "hf_model": {
           "path": "hf_model:metrics/scope_claims_audit.json",
           "exists": true,
           "bytes": 21313,
-          "sha256": "a03133115a089d88dc3ce87f831674603d8b252138790693d8def878b9264da0"
+          "sha256": "b997454e0e9bb382da0afcdec319086081213d176546306e13a7d47d42e8957c"
         }
       },
       "failures": []
@@ -1756,44 +1756,44 @@
         "path": "repo:docs/data/source_alignment_audit.json",
         "exists": true,
         "bytes": 4432,
-        "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+        "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model_data": {
           "path": "hf_model:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         },
         "hf_model": {
           "path": "hf_model:metrics/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "6173b5fb5e1c69983f5a2b83288d521968de16810f8e01bd2717b99a67f4285c"
+          "sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
         }
       },
       "failures": []
@@ -1853,45 +1853,45 @@
       "local": {
         "path": "repo:docs/data/single_episode_task_model_radar.json",
         "exists": true,
-        "bytes": 51327,
-        "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+        "bytes": 52866,
+        "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model_data": {
           "path": "hf_model:data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         },
         "hf_model": {
           "path": "hf_model:metrics/single_episode_task_model_radar.json",
           "exists": true,
-          "bytes": 51327,
-          "sha256": "791793dc1dc1655dcae8803300def7f9e7e2c84b5af6321cbb1561c76bff2e7c"
+          "bytes": 52866,
+          "sha256": "804273420658eae853df3d1c1f45f83040fb09551c74c203bb833d73b6c2a4c1"
         }
       },
       "failures": []
@@ -1902,45 +1902,45 @@
       "local": {
         "path": "repo:docs/data/episode128_task_model_radar.json",
         "exists": true,
-        "bytes": 185212,
-        "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+        "bytes": 186997,
+        "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model_data": {
           "path": "hf_model:data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         },
         "hf_model": {
           "path": "hf_model:metrics/episode128_task_model_radar.json",
           "exists": true,
-          "bytes": 185212,
-          "sha256": "f3007f5799e2bb92ab9891bcdfd1f0f63dfef6452198d44e2b3f8d38a5493859"
+          "bytes": 186997,
+          "sha256": "d15869d177f5a9cc37e20d0cab62fdc1be61d596975fee13a5d1d61108c7176a"
         }
       },
       "failures": []
@@ -2197,44 +2197,44 @@
         "path": "repo:docs/data/task_surface_integrity.json",
         "exists": true,
         "bytes": 46246,
-        "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+        "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_surface_integrity.json",
           "exists": true,
           "bytes": 46246,
-          "sha256": "d4437d2ae8900c75122057be8739b4812da61b91f7495a97271844e9ad33d539"
+          "sha256": "e85510c4a7df9e1fd43651d18291b51b1ad2c3ab0b5042d4edc2a598a1929556"
         }
       },
       "failures": []
@@ -2294,45 +2294,45 @@
       "local": {
         "path": "repo:docs/data/task_method_20_result_matrix.json",
         "exists": true,
-        "bytes": 128509,
-        "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+        "bytes": 128991,
+        "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_method_20_result_matrix.json",
           "exists": true,
-          "bytes": 128509,
-          "sha256": "d5002c1a36f0c4dc15f184de2480fb123aee5a80ae1f6c5a964c449c1c97cd54"
+          "bytes": 128991,
+          "sha256": "c070f4430cff2583e150cb66ed75b5759ee985429af7aa22a8a83c14a5a8841f"
         }
       },
       "failures": []
@@ -2490,45 +2490,45 @@
       "local": {
         "path": "repo:docs/data/unified_task_model_radar.json",
         "exists": true,
-        "bytes": 229035,
-        "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+        "bytes": 230938,
+        "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model_data": {
           "path": "hf_model:data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         },
         "hf_model": {
           "path": "hf_model:metrics/unified_task_model_radar.json",
           "exists": true,
-          "bytes": 229035,
-          "sha256": "c810377ee743c0ad251eb77b1549d4e096c581fa861da46b9e0fd1f2dce46a22"
+          "bytes": 230938,
+          "sha256": "e9523c3f97d6493058030ad05c3a8a80c51a11727fbf8eb936c405ac986531c1"
         }
       },
       "failures": []
@@ -2540,44 +2540,44 @@
         "path": "repo:docs/data/website_integrity.json",
         "exists": true,
         "bytes": 20178,
-        "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+        "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model_data": {
           "path": "hf_model:data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         },
         "hf_model": {
           "path": "hf_model:metrics/website_integrity.json",
           "exists": true,
           "bytes": 20178,
-          "sha256": "d9e72c5e628c9ed808a7a4648e29fbca9a455ff2ae466abde9cabd27f2f87e6a"
+          "sha256": "b24c99ae7b5f9ae9fd48f04f39728979aabec7d79eaad1a0ed4437e02a7cb218"
         }
       },
       "failures": []
@@ -2760,33 +2760,33 @@
       "local": {
         "path": "repo:docs/assets/charts/single_episode_task_model_radar.svg",
         "exists": true,
-        "bytes": 35232,
-        "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+        "bytes": 36930,
+        "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/single_episode_task_model_radar.svg",
           "exists": true,
-          "bytes": 35232,
-          "sha256": "87b52a7dead40358f1778dda43ade4d2e875ac98e507e01ca007084363e5977e"
+          "bytes": 36930,
+          "sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
         }
       },
       "failures": []
@@ -2797,33 +2797,33 @@
       "local": {
         "path": "repo:docs/assets/charts/episode128_task_model_radar.svg",
         "exists": true,
-        "bytes": 51915,
-        "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+        "bytes": 79370,
+        "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/episode128_task_model_radar.svg",
           "exists": true,
-          "bytes": 51915,
-          "sha256": "047ea4b05a04f6734e2afcf792863559dc8f3091eae88a97ff90e8b038a423f4"
+          "bytes": 79370,
+          "sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
         }
       },
       "failures": []
@@ -2871,33 +2871,33 @@
       "local": {
         "path": "repo:docs/assets/charts/unified_task_model_radar.svg",
         "exists": true,
-        "bytes": 57938,
-        "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+        "bytes": 98527,
+        "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_artifacts_card": {
           "path": "hf_artifacts:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         },
         "hf_model": {
           "path": "hf_model:assets/charts/unified_task_model_radar.svg",
           "exists": true,
-          "bytes": 57938,
-          "sha256": "bb83b80b47fe679ebdce2c99378a4548120f1c8cc2d725b88e409d8c386dcbf8"
+          "bytes": 98527,
+          "sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
         }
       },
       "failures": []
@@ -5327,21 +5327,21 @@
       "local": {
         "path": "repo:scripts/build_artifact_index.py",
         "exists": true,
-        "bytes": 68279,
-        "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+        "bytes": 68407,
+        "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 68279,
-          "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+          "bytes": 68407,
+          "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 68279,
-          "sha256": "69b43ad5d3dc5a6893c4592fa47fff6a7a87691728ec2c61b121ec262d00bf2a"
+          "bytes": 68407,
+          "sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
         }
       },
       "failures": []
@@ -5402,21 +5402,21 @@
       "local": {
         "path": "repo:scripts/build_figure_index.py",
         "exists": true,
-        "bytes": 16845,
-        "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+        "bytes": 16886,
+        "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_figure_index.py",
           "exists": true,
-          "bytes": 16845,
-          "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+          "bytes": 16886,
+          "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_figure_index.py",
           "exists": true,
-          "bytes": 16845,
-          "sha256": "3f91f7f13a3fb08ab57c2f0a6b320102e9d5ae19b102b71499edb5b8fd5a2cec"
+          "bytes": 16886,
+          "sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
         }
       },
       "failures": []
@@ -5877,21 +5877,21 @@
       "local": {
         "path": "repo:scripts/build_unified_task_model_radar.py",
         "exists": true,
-        "bytes": 69956,
-        "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+        "bytes": 78735,
+        "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_unified_task_model_radar.py",
           "exists": true,
-          "bytes": 69956,
-          "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+          "bytes": 78735,
+          "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_unified_task_model_radar.py",
           "exists": true,
-          "bytes": 69956,
-          "sha256": "3d137eced3c376ed674090b823ff9439cea0e8e8670ea9de02c3d3781305a0c9"
+          "bytes": 78735,
+          "sha256": "8e7110381d56e5ef0effb7dcc7935d1bb0ce2653289504a50d04f29571a4e6b7"
         }
       },
       "failures": []
@@ -6331,39 +6331,39 @@
       "local": {
         "path": "repo:docs/index.html",
         "exists": true,
-        "bytes": 348267,
-        "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+        "bytes": 348384,
+        "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_artifacts_root": {
           "path": "hf_artifacts:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_model": {
           "path": "hf_model:index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         },
         "hf_model_docs": {
           "path": "hf_model:docs/index.html",
           "exists": true,
-          "bytes": 348267,
-          "sha256": "8e6ac665f1a0e810667379733013a906d3f13a390bceb4b41594769aa773626d"
+          "bytes": 348384,
+          "sha256": "6f6b2c6b40e8d38210fd2e0c04750732afb5179996a663185f2525442c9c957a"
         }
       },
       "failures": []
@@ -31027,27 +31027,27 @@
       "local": {
         "path": "repo:FIGURE_INDEX.md",
         "exists": true,
-        "bytes": 7027,
-        "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+        "bytes": 7068,
+        "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         },
         "hf_model": {
           "path": "hf_model:FIGURE_INDEX.md",
           "exists": true,
-          "bytes": 7027,
-          "sha256": "b7b507c35cd3cba2765586e9703a447c8025c89658c3daa390df67db4211d0fc"
+          "bytes": 7068,
+          "sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
         }
       },
       "failures": []
@@ -31554,27 +31554,27 @@
       "local": {
         "path": "repo:TASK_METHOD_20_RESULT_MATRIX.md",
         "exists": true,
-        "bytes": 14715,
-        "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+        "bytes": 14862,
+        "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         },
         "hf_model": {
           "path": "hf_model:TASK_METHOD_20_RESULT_MATRIX.md",
           "exists": true,
-          "bytes": 14715,
-          "sha256": "acf665d5c07f15224b42d9da93bc2586279852bd60241868391ba7c0a462a24f"
+          "bytes": 14862,
+          "sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
         }
       },
       "failures": []

metrics/public_surface_qa.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Public Project Surface",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:01:39+00:00",
+  "generated_at_utc": "2026-06-21T20:35:18+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": "2026-06-21T20:01:18+00:00"
+          "generated_at_utc": "2026-06-21T20:35:18+00:00"
         },
         "rendered_site_check": {
           "exists": true,
@@ -28,27 +28,27 @@
         "task_surface_integrity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T15:21:55+00:00"
+          "generated_at_utc": "2026-06-21T20:30:48+00:00"
         },
         "source_alignment": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T15:21:55+00:00"
+          "generated_at_utc": "2026-06-21T20:30:47+00:00"
         },
         "scale_up_status": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T15:23:13+00:00"
+          "generated_at_utc": "2026-06-21T20:30:47+00:00"
         },
         "publication_package": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T19:57:53+00:00"
+          "generated_at_utc": "2026-06-21T20:32:45+00:00"
         },
         "mirror_parity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-21T20:00:18+00:00"
+          "generated_at_utc": "2026-06-21T20:33:57+00:00"
         }
       },
       "failures": {}
@@ -97,8 +97,8 @@
       "marker_counts": {
         "Ropedia Xperience-10M Task Suite": 22,
         "Xperience-10M": 173,
-        "20-task": 110,
-        "Qwen3-Omni": 246,
+        "20-task": 107,
+        "Qwen3-Omni": 239,
         "128-episode pilot": 1
       }
     },

metrics/publication_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:02:09+00:00",
+  "generated_at_utc": "2026-06-21T20:35:41+00:00",
   "checks": [
     {
       "name": "required_publication_assets_present",

metrics/quality_gates.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Release Checks",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:21:42+00:00",
+  "generated_at_utc": "2026-06-21T20:35:18+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": [
     {

metrics/scope_claims_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:23:13+00:00",
+  "generated_at_utc": "2026-06-21T20:35:22+00:00",
   "summary": {
     "qwen3_omni_verified_diagnostic_pilot": true,
     "dataset_manifest_num_episodes": 119,

metrics/single_episode_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "Single-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+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,
@@ -11,10 +11,28 @@
     "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",
     "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
+    "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
     "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
-    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 points are plotted only on task-aligned axes. Scoreless records mean the public result does not evaluate that task contract.",
-    "metadata_128_overlay": "128-episode aligned baselines have 20 records. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists; raw interaction text and paired camera-view embeddings remain explicit gaps.",
-    "raw_128_overlay": "128-episode raw-feature baselines use staged sensor NPZ features. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
+    "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
+    "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+  },
+  "chart_design": {
+    "mode": "grouped_small_multiples",
+    "method_count": 2,
+    "reason": "This split view has 2 methods and 40 method-task records; grouped radar panels keep related methods readable while retaining the unified source matrix.",
+    "groups": [
+      {
+        "id": "single_episode",
+        "title": "Single-episode sample",
+        "series_ids": [
+          "minimal",
+          "neural_mlp"
+        ]
+      }
+    ],
+    "visual_radius_transform": "sqrt(normalized_score)",
+    "exact_value_source": "docs/data/task_method_20_result_matrix.json"
   },
   "source_unified_radar": "docs/data/unified_task_model_radar.json",
   "source_result_matrix": "docs/data/task_method_20_result_matrix.json",
@@ -28,7 +46,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode simple heads over the public sample split.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -51,7 +69,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

metrics/source_alignment_audit.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Source Alignment Note",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:21:55+00:00",
+  "generated_at_utc": "2026-06-21T20:35:22+00:00",
   "alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
   "alignment_summary": {
     "full_dataset_repo": "ropedia-ai/xperience-10m",

metrics/task_method_20_result_matrix.json

@@ -1,7 +1,7 @@
 {
   "title": "Task Method 20-Result Matrix",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
@@ -16,7 +16,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode simple heads over the public sample split.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -39,7 +39,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -62,7 +62,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "9 6",
       "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -86,7 +86,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "3 6",
       "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -110,7 +110,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "8 4",
       "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -134,7 +134,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "2 5",
       "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -158,7 +158,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
       "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -181,7 +181,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
       "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -204,7 +204,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "2 7",
       "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

metrics/task_surface_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:21:55+00:00",
+  "generated_at_utc": "2026-06-21T20:35:22+00:00",
   "summary": {
     "original_walkthrough_task_count": 12,
     "expected_original_walkthrough_task_count": 12,

metrics/unified_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "Unified 20-Task Model Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T15:20:34+00:00",
+  "generated_at_utc": "2026-06-21T20:35:16+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
@@ -10,10 +10,53 @@
     "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",
     "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
+    "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
     "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
-    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 points are plotted only on task-aligned axes. Scoreless records mean the public result does not evaluate that task contract.",
-    "metadata_128_overlay": "128-episode aligned baselines have 20 records. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists; raw interaction text and paired camera-view embeddings remain explicit gaps.",
-    "raw_128_overlay": "128-episode raw-feature baselines use staged sensor NPZ features. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+    "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
+    "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
+    "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
+  },
+  "chart_design": {
+    "mode": "grouped_small_multiples",
+    "method_count": 9,
+    "reason": "The public release has nine methods and 180 scored records; small-multiple radar panels avoid a nine-polygon overlay while keeping every method visible.",
+    "groups": [
+      {
+        "id": "single_episode",
+        "title": "Single-episode sample",
+        "series_ids": [
+          "minimal",
+          "neural_mlp"
+        ]
+      },
+      {
+        "id": "metadata_128",
+        "title": "128-episode metadata/text",
+        "series_ids": [
+          "metadata128_simple",
+          "metadata128_neural_mlp"
+        ]
+      },
+      {
+        "id": "raw_128",
+        "title": "128-episode raw features",
+        "series_ids": [
+          "raw128_simple",
+          "raw128_neural_mlp"
+        ]
+      },
+      {
+        "id": "foundation_models",
+        "title": "Foundation-model probes",
+        "series_ids": [
+          "qwen3_omni_v6_lora",
+          "cosmos3_super_reasoner",
+          "cosmos3_nano_future_window"
+        ]
+      }
+    ],
+    "visual_radius_transform": "sqrt(normalized_score)",
+    "exact_value_source": "docs/data/task_method_20_result_matrix.json"
   },
   "series": [
     {
@@ -25,7 +68,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode simple heads over the public sample split.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -48,7 +91,7 @@
       "scope": "1 public sample episode",
       "stroke_dasharray": null,
       "method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
-      "plotted_as": "filled polygon",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -71,7 +114,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "9 6",
       "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -95,7 +138,7 @@
       "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
       "stroke_dasharray": "3 6",
       "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -119,7 +162,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "8 4",
       "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -143,7 +186,7 @@
       "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
       "stroke_dasharray": "2 5",
       "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -167,7 +210,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "7 7",
       "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -190,7 +233,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "4 7",
       "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,
@@ -213,7 +256,7 @@
       "scope": "128 selected episodes, held-out test",
       "stroke_dasharray": "2 7",
       "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
-      "plotted_as": "colored point overlay",
+      "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
       "result_record_count": 20,
       "scored_task_count": 20,
       "covered_task_count": 20,

metrics/website_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-21T20:01:18+00:00",
+  "generated_at_utc": "2026-06-21T20:35:18+00:00",
   "docs_root": "docs",
   "site_base": "/ropedia-xperience-10m-task-suite/",
   "summary": {
@@ -80,8 +80,8 @@
       "name": "project_overview_precedes_progress_ledger",
       "status": "pass",
       "reason": "The project overview should appear before the deeper progress ledger.",
-      "overview_index": 136413,
-      "evidence_index": 187740
+      "overview_index": 136346,
+      "evidence_index": 187681
     },
     {
       "name": "project_status_links_json",
@@ -159,9 +159,9 @@
       "name": "evaluation_protocol_between_overview_and_progress",
       "status": "pass",
       "reason": "The evaluation protocol should appear before the deeper evidence ledger.",
-      "overview_index": 136413,
-      "protocol_index": 183928,
-      "evidence_index": 187740
+      "overview_index": 136346,
+      "protocol_index": 183869,
+      "evidence_index": 187681
     },
     {
       "name": "evaluation_protocol_links_json",
@@ -187,7 +187,7 @@
       "status": "pass",
       "reason": "The Suite anchor should show the task-suite map before the radar/results surface.",
       "first_marker_index": 468,
-      "second_marker_index": 1838
+      "second_marker_index": 2000
     },
     {
       "name": "raw_sample_stream_ledger_contains_seven_modalities",
@@ -315,7 +315,7 @@
     },
     {
       "path": "data/artifact_index.json",
-      "bytes": 124341,
+      "bytes": 124471,
       "top_level_type": "dict"
     },
     {
@@ -330,7 +330,7 @@
     },
     {
       "path": "data/episode128_task_model_radar.json",
-      "bytes": 185212,
+      "bytes": 186828,
       "top_level_type": "dict"
     },
     {
@@ -345,7 +345,7 @@
     },
     {
       "path": "data/figure_index.json",
-      "bytes": 19485,
+      "bytes": 19526,
       "top_level_type": "dict"
     },
     {
@@ -495,7 +495,7 @@
     },
     {
       "path": "data/single_episode_task_model_radar.json",
-      "bytes": 51327,
+      "bytes": 52256,
       "top_level_type": "dict"
     },
     {
@@ -515,7 +515,7 @@
     },
     {
       "path": "data/task_method_20_result_matrix.json",
-      "bytes": 128509,
+      "bytes": 128991,
       "top_level_type": "dict"
     },
     {
@@ -565,7 +565,7 @@
     },
     {
       "path": "data/unified_task_model_radar.json",
-      "bytes": 229035,
+      "bytes": 230938,
       "top_level_type": "dict"
     },
     {
@@ -610,7 +610,7 @@
     {
       "path": "assets/charts/episode128_task_model_radar.svg",
       "exists": true,
-      "bytes": 51915,
+      "bytes": 79370,
       "format": "SVG",
       "has_viewbox": true
     },
@@ -666,7 +666,7 @@
     {
       "path": "assets/charts/single_episode_task_model_radar.svg",
       "exists": true,
-      "bytes": 35232,
+      "bytes": 36930,
       "format": "SVG",
       "has_viewbox": true
     },
@@ -680,7 +680,7 @@
     {
       "path": "assets/charts/unified_task_model_radar.svg",
       "exists": true,
-      "bytes": 57938,
+      "bytes": 98527,
       "format": "SVG",
       "has_viewbox": true
     },

scripts/build_artifact_index.py

@@ -539,7 +539,7 @@ ARTIFACTS = [
         "path": "docs/data/unified_task_model_radar.json",
         "kind": "website_data",
         "surface": "website_hf",
-        "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3-Omni/Cosmos3 overlay mappings, method-card caveats, proxy flags, and source artifacts.",
+        "shows": "Stores normalized 20-axis radar values, raw task metrics, grouped chart-design metadata, Qwen3-Omni/Cosmos3 source mappings, method-card caveats, proxy flags, and source artifacts.",
     },
     {
         "id": "single_episode_task_model_radar_json",
@@ -619,7 +619,7 @@ ARTIFACTS = [
         "path": "docs/assets/charts/unified_task_model_radar.svg",
         "kind": "generated_figure",
         "surface": "website_hf",
-        "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3-Omni and Cosmos3 task-aligned overlays.",
+        "shows": "Groups all nine methods into small-multiple 20-task radar panels so single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows remain readable.",
     },
     {
         "id": "single_episode_task_model_radar_chart",
@@ -627,7 +627,7 @@ ARTIFACTS = [
         "path": "docs/assets/charts/single_episode_task_model_radar.svg",
         "kind": "generated_figure",
         "surface": "website_hf",
-        "shows": "Separates the one-episode Minimal and Neural MLP 20/20 scored baselines into a clean two-polygon radar.",
+        "shows": "Shows the one-episode Minimal and Neural MLP 20/20 scored baselines in one enlarged radar panel with local legend and task key.",
     },
     {
         "id": "episode128_task_model_radar_chart",
@@ -635,7 +635,7 @@ ARTIFACTS = [
         "path": "docs/assets/charts/episode128_task_model_radar.svg",
         "kind": "generated_figure",
         "surface": "website_hf",
-        "shows": "Separates the selected 128-episode methods: raw-feature simple/NN as complete 20/20 scored polygons plus metadata, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano task-aligned overlays.",
+        "shows": "Separates selected 128-episode methods into metadata/text, raw-feature, and foundation-model radar panels with all 140 result rows scored and proxy notes retained.",
     },
     {
         "id": "unified_task_model_radar_builder",
@@ -643,7 +643,7 @@ ARTIFACTS = [
         "path": "scripts/build_unified_task_model_radar.py",
         "kind": "visualization_builder",
         "surface": "repo_hf",
-        "shows": "Regenerates the direction-aware radar chart and machine-readable metric overlay JSON.",
+        "shows": "Regenerates grouped 20-task radar charts plus machine-readable metric, source, chart-design, and proxy metadata.",
     },
     {
         "id": "task_method_20_gap_audit_builder",

scripts/build_figure_index.py

@@ -206,7 +206,7 @@ FIGURES = [
         "id": "unified_task_model_radar",
         "title": "Unified 20-task model radar",
         "path": "docs/assets/charts/unified_task_model_radar.svg",
-        "role": "Twenty-axis direction-aware comparison of minimal and neural MLP baselines, with 128-episode metadata, Qwen3, and Cosmos task-aligned overlay points and branch notes.",
+        "role": "Grouped small-multiple 20-task radar board for all nine methods, separating single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows while preserving task keys and proxy notes.",
         "source_script": "scripts/build_unified_task_model_radar.py",
         "surface": "website unified task section, README, HF mirrors",
     },
@@ -222,7 +222,7 @@ FIGURES = [
         "id": "episode128_task_model_radar",
         "title": "128-episode 20-task model radar",
         "path": "docs/assets/charts/episode128_task_model_radar.svg",
-        "role": "Twenty-axis split radar for selected 128-episode methods: raw-feature simple/NN as complete scored polygons plus metadata, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano task-aligned overlays.",
+        "role": "Grouped 20-task radar for selected 128-episode methods: metadata/text baselines, raw-feature simple/NN, Qwen3-Omni, Cosmos3-Super, and Cosmos3-Nano with local legends and proxy notes.",
         "source_script": "scripts/build_unified_task_model_radar.py",
         "surface": "website unified task section, README, HF mirrors",
     },

scripts/build_unified_task_model_radar.py

@@ -503,6 +503,33 @@ EPISODE128_SERIES = (
     "cosmos3_nano_future_window",
 )
 
+RADAR_GROUP_SPECS = (
+    {
+        "id": "single_episode",
+        "title": "Single-episode sample",
+        "subtitle": "Public-sample simple and neural task heads.",
+        "series_ids": ("minimal", "neural_mlp"),
+    },
+    {
+        "id": "metadata_128",
+        "title": "128-episode metadata/text",
+        "subtitle": "Aligned JSONL metadata/text plus staged target blocks.",
+        "series_ids": ("metadata128_simple", "metadata128_neural_mlp"),
+    },
+    {
+        "id": "raw_128",
+        "title": "128-episode raw features",
+        "subtitle": "4430-dim sensor-block heads; proxy axes are flagged.",
+        "series_ids": ("raw128_simple", "raw128_neural_mlp"),
+    },
+    {
+        "id": "foundation_models",
+        "title": "Foundation-model probes",
+        "subtitle": "Verified Qwen3 and Cosmos task-specific outputs.",
+        "series_ids": ("qwen3_omni_v6_lora", "cosmos3_super_reasoner", "cosmos3_nano_future_window"),
+    },
+)
+
 STATUS_LABELS = {
     "scored": "scored",
     "proxy_scored": "proxy scored",
@@ -760,7 +787,7 @@ def render_matrix_markdown(payload: dict[str, Any]) -> str:
             "",
             "## Compact Score Matrix",
             "",
-            "Cells show `raw metric value`, then `direct/proxy; normalized radar value; metric key`. The raw metric is the value to cite; the normalized value is the 0-1 plotting value used by the radar.",
+            "Cells show `raw metric value`, then `direct/proxy; normalized radar value; metric key`. The raw metric is the value to cite; the normalized value is the exact linear 0-1 score retained in JSON. The SVG radar uses sqrt(normalized score) only for visual radius, so low but real differences remain visible without changing the table values.",
             "",
             "| # | Task | " + " | ".join(spec["short_label"] for spec in SERIES.values()) + " |",
             "| ---: | --- | " + " | ".join("---" for _ in SERIES) + " |",
@@ -814,6 +841,21 @@ def filtered_radar_payload(
         for row in payload["task_method_result_matrix"]
         if row.get("series_id") in selected
     ]
+    selected_groups = radar_groups_for_series(series_ids)
+    chart_design = json.loads(json.dumps(payload.get("chart_design", {})))
+    chart_design["method_count"] = len(series)
+    chart_design["reason"] = (
+        f"This split view has {len(series)} methods and {sum(record.get('result_record_count', 0) for record in series)} "
+        "method-task records; grouped radar panels keep related methods readable while retaining the unified source matrix."
+    )
+    chart_design["groups"] = [
+        {
+            "id": group["id"],
+            "title": group["title"],
+            "series_ids": list(group["series_ids"]),
+        }
+        for group in selected_groups
+    ]
     return {
         "title": title,
         "status": payload["status"],
@@ -824,6 +866,7 @@ def filtered_radar_payload(
         "method_task_record_count": sum(record.get("result_record_count", 0) for record in series),
         "scored_method_task_count": sum(record.get("scored_task_count", 0) for record in series),
         "normalization_policy": payload["normalization_policy"],
+        "chart_design": chart_design,
         "source_unified_radar": "docs/data/unified_task_model_radar.json",
         "source_result_matrix": "docs/data/task_method_20_result_matrix.json",
         "series": series,
@@ -1016,7 +1059,7 @@ def build_payload() -> dict[str, Any]:
                 "id": series_id,
                 **spec,
                 "method_detail": METHOD_DETAILS.get(series_id, spec["scope"]),
-                "plotted_as": "filled polygon" if spec["kind"].startswith("full_20_task_baseline") else "colored point overlay",
+                "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
                 "result_record_count": len(tasks),
                 "scored_task_count": covered,
                 "covered_task_count": covered,
@@ -1049,10 +1092,26 @@ def build_payload() -> dict[str, Any]:
             "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",
             "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
+            "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
             "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
-            "foundation_model_overlay": "Qwen3-Omni and Cosmos3 points are plotted only on task-aligned axes. Scoreless records mean the public result does not evaluate that task contract.",
-            "metadata_128_overlay": "128-episode aligned baselines have 20 records. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists; raw interaction text and paired camera-view embeddings remain explicit gaps.",
-            "raw_128_overlay": "128-episode raw-feature baselines use staged sensor NPZ features. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export.",
+            "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
+            "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
+            "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export.",
+        },
+        "chart_design": {
+            "mode": "grouped_small_multiples",
+            "method_count": len(SERIES),
+            "reason": "The public release has nine methods and 180 scored records; small-multiple radar panels avoid a nine-polygon overlay while keeping every method visible.",
+            "groups": [
+                {
+                    "id": group["id"],
+                    "title": group["title"],
+                    "series_ids": list(group["series_ids"]),
+                }
+                for group in RADAR_GROUP_SPECS
+            ],
+            "visual_radius_transform": "sqrt(normalized_score)",
+            "exact_value_source": "docs/data/task_method_20_result_matrix.json",
         },
         "series": series_records,
         "tasks": tasks,
@@ -1128,6 +1187,266 @@ def build_payload() -> dict[str, Any]:
     return payload
 
 
+def svg_shape(
+    tag: str,
+    points: list[tuple[float, float]],
+    *,
+    fill: str,
+    fill_opacity: float,
+    stroke: str,
+    stroke_opacity: float = 0.92,
+    stroke_width: float = 2.0,
+    dash: str | None = None,
+) -> str:
+    coords = " ".join(f"{x:.1f},{y:.1f}" for x, y in points)
+    dash_attr = f' stroke-dasharray="{dash}"' if dash else ""
+    return (
+        f'<{tag} points="{coords}" fill="{fill}" fill-opacity="{fill_opacity:.3f}" '
+        f'stroke="{stroke}" stroke-opacity="{stroke_opacity:.3f}" stroke-width="{stroke_width:.1f}" '
+        f'stroke-linejoin="round" stroke-linecap="round"{dash_attr}/>'
+    )
+
+
+def radar_radius(score: float | None, radius: float) -> float | None:
+    if score is None:
+        return None
+    return radius * math.sqrt(clamp01(float(score)))
+
+
+def radar_groups_for_series(series_ids: tuple[str, ...]) -> list[dict[str, Any]]:
+    selected = set(series_ids)
+    groups: list[dict[str, Any]] = []
+    assigned: set[str] = set()
+    for group in RADAR_GROUP_SPECS:
+        present = tuple(series_id for series_id in group["series_ids"] if series_id in selected)
+        if not present:
+            continue
+        groups.append({**group, "series_ids": present})
+        assigned.update(present)
+    remaining = tuple(series_id for series_id in series_ids if series_id not in assigned)
+    if remaining:
+        groups.append(
+            {
+                "id": "other_methods",
+                "title": "Other methods",
+                "subtitle": "Additional method rows retained from the matrix.",
+                "series_ids": remaining,
+            }
+        )
+    return groups
+
+
+def draw_radar_grid(
+    parts: list[str],
+    *,
+    cx: float,
+    cy: float,
+    radius: float,
+    tasks: list[dict[str, Any]],
+    angles: list[float],
+    label_size: int,
+) -> None:
+    for value in (0.05, 0.25, 0.50, 0.75, 1.0):
+        ring_radius = radius * math.sqrt(value)
+        ring = [point(cx, cy, ring_radius, angle) for angle in angles]
+        parts.append(
+            svg_shape(
+                "polygon",
+                ring,
+                fill="none",
+                fill_opacity=0,
+                stroke="#ccffa0",
+                stroke_opacity=0.16,
+                stroke_width=1.0,
+            )
+        )
+        parts.append(svg_text(cx + 8, cy - ring_radius + 4, f"{value:.2g}", size=max(9, label_size - 2), fill="#a5afa2", weight=620, opacity=0.72))
+    for task, angle in zip(tasks, angles):
+        x, y = point(cx, cy, radius, angle)
+        parts.append(f'<line x1="{cx:.1f}" y1="{cy:.1f}" x2="{x:.1f}" y2="{y:.1f}" stroke="#ccffa0" stroke-opacity="0.11" stroke-width="1"/>')
+        lx, ly = point(cx, cy, radius + 28, angle)
+        proxy = task["task_id"] in PROXY_TASK_IDS
+        color = "#f472b6" if proxy else "#ccffa0"
+        parts.append(f'<circle cx="{lx:.1f}" cy="{ly:.1f}" r="{label_size + 2:.1f}" fill="{color}" fill-opacity="0.12" stroke="{color}" stroke-opacity="0.34"/>')
+        parts.append(svg_text(lx, ly + label_size * 0.33, f"{task['task_number']:02d}", size=label_size, fill=color, anchor="middle", weight=850, opacity=0.98))
+
+
+def draw_radar_series(
+    parts: list[str],
+    *,
+    cx: float,
+    cy: float,
+    radius: float,
+    tasks: list[dict[str, Any]],
+    angles: list[float],
+    series_id: str,
+    stroke_width: float,
+    fill_opacity: float,
+) -> None:
+    spec = SERIES[series_id]
+    valid_points: list[tuple[float, float]] = []
+    scored_count = 0
+    for task, angle in zip(tasks, angles):
+        value = task["values"].get(series_id, {})
+        score = value.get("normalized_score")
+        plotted_radius = radar_radius(score, radius)
+        if plotted_radius is None:
+            continue
+        scored_count += 1
+        valid_points.append(point(cx, cy, plotted_radius, angle))
+    if len(valid_points) >= 3 and scored_count == len(tasks):
+        parts.append(
+            svg_shape(
+                "polygon",
+                valid_points,
+                fill=spec["color"],
+                fill_opacity=fill_opacity,
+                stroke=spec["color"],
+                stroke_width=stroke_width,
+                dash=spec.get("stroke_dasharray"),
+            )
+        )
+    elif len(valid_points) >= 2:
+        parts.append(
+            svg_shape(
+                "polyline",
+                valid_points,
+                fill="none",
+                fill_opacity=0,
+                stroke=spec["color"],
+                stroke_width=stroke_width,
+                dash=spec.get("stroke_dasharray"),
+            )
+        )
+    for task, angle in zip(tasks, angles):
+        value = task["values"].get(series_id, {})
+        plotted_radius = radar_radius(value.get("normalized_score"), radius)
+        if plotted_radius is None:
+            continue
+        px, py = point(cx, cy, plotted_radius, angle)
+        proxy = value.get("status") == "proxy_scored"
+        parts.append(
+            f'<circle cx="{px:.1f}" cy="{py:.1f}" r="{5.5 if proxy else 4.4:.1f}" '
+            f'fill="{spec["color"]}" fill-opacity="0.95" stroke="{"#f4f8ef" if proxy else "#020502"}" '
+            f'stroke-width="{2.1 if proxy else 1.3:.1f}"/>'
+        )
+
+
+def draw_radar_panel(
+    parts: list[str],
+    *,
+    x: float,
+    y: float,
+    width: float,
+    height: float,
+    group: dict[str, Any],
+    payload: dict[str, Any],
+    series_record_by_id: dict[str, dict[str, Any]],
+    large: bool = False,
+) -> None:
+    tasks = payload["tasks"]
+    angles = [-math.pi / 2 + 2 * math.pi * i / len(tasks) for i in range(len(tasks))]
+    panel_bg = "#071007"
+    parts.append(f'<rect x="{x:.1f}" y="{y:.1f}" width="{width:.1f}" height="{height:.1f}" rx="18" fill="{panel_bg}" fill-opacity="0.90" stroke="#ccffa0" stroke-opacity="0.22"/>')
+    parts.append(svg_text(x + 28, y + 44, str(group["title"]), size=26 if large else 20, weight=850))
+    parts.append(svg_text(x + 28, y + 74, str(group["subtitle"]), size=14 if large else 12, fill="#a5afa2", weight=600))
+
+    if large:
+        cx = x + width * 0.39
+        cy = y + height * 0.56
+        radius = min(width * 0.20, height * 0.34)
+        legend_x = x + width * 0.68
+        legend_y = y + 160
+        label_size = 12
+    else:
+        cx = x + width * 0.38
+        cy = y + height * 0.57
+        radius = min(width * 0.18, height * 0.30)
+        legend_x = x + width * 0.67
+        legend_y = y + 122
+        label_size = 8
+
+    draw_radar_grid(parts, cx=cx, cy=cy, radius=radius, tasks=tasks, angles=angles, label_size=label_size)
+
+    series_ids = tuple(group["series_ids"])
+    fill_opacity = 0.065 if len(series_ids) <= 2 else 0.040
+    for idx, series_id in enumerate(series_ids):
+        draw_radar_series(
+            parts,
+            cx=cx,
+            cy=cy,
+            radius=radius,
+            tasks=tasks,
+            angles=angles,
+            series_id=series_id,
+            stroke_width=4.3 if large else 3.2,
+            fill_opacity=max(0.026, fill_opacity - idx * 0.010),
+        )
+
+    parts.append(svg_text(legend_x, legend_y - 34, "Methods", size=17 if large else 14, fill="#ccffa0", weight=850))
+    for idx, series_id in enumerate(series_ids):
+        record = series_record_by_id[series_id]
+        color = record["color"]
+        row_y = legend_y + idx * (92 if large else 74)
+        parts.append(f'<line x1="{legend_x:.1f}" y1="{row_y:.1f}" x2="{legend_x + 58:.1f}" y2="{row_y:.1f}" stroke="{color}" stroke-width="{6 if large else 5}" stroke-linecap="round" stroke-dasharray="{record.get("stroke_dasharray") or ""}"/>')
+        parts.append(f'<circle cx="{legend_x + 29:.1f}" cy="{row_y:.1f}" r="{6 if large else 5}" fill="{color}" stroke="#020502" stroke-width="1.5"/>')
+        parts.append(svg_text(legend_x + 74, row_y + 5, record["label"], size=15 if large else 12, weight=850))
+        coverage = f"{record['scored_task_count']}/20 scored"
+        proxy = record.get("proxy_scored_task_count", 0)
+        if proxy:
+            coverage += f" · {proxy} proxy"
+        parts.append(svg_text(legend_x + 74, row_y + (28 if large else 22), coverage, size=12 if large else 10, fill=color, weight=800))
+        detail = split_text(METHOD_DETAILS.get(series_id, record["scope"]), 50 if large else 44)[:2]
+        parts.extend(svg_text_lines(legend_x + 74, row_y + (49 if large else 40), detail, size=10 if large else 8, fill="#a5afa2", weight=560, line_height=13 if large else 10))
+
+    parts.append(svg_text(x + 28, y + height - 30, "Radius = sqrt(normalized score); exact raw and normalized values are in the matrix.", size=11 if large else 9, fill="#a5afa2", weight=600, opacity=0.88))
+
+
+def draw_task_key(parts: list[str], *, x: float, y: float, width: float, tasks: list[dict[str, Any]], compact: bool = False) -> None:
+    height = 292 if not compact else 250
+    parts.append(f'<rect x="{x:.1f}" y="{y:.1f}" width="{width:.1f}" height="{height:.1f}" rx="16" fill="#020502" fill-opacity="0.62" stroke="#ccffa0" stroke-opacity="0.18"/>')
+    parts.append(svg_text(x + 28, y + 42, "20-task axis key", size=20, weight=850))
+    parts.append(svg_text(x + 250, y + 42, "Task numbers stay on the radar; full names and proxy axes stay here.", size=13, fill="#a5afa2", weight=600))
+    col_count = 4
+    col_w = (width - 56) / col_count
+    row_h = 42 if not compact else 36
+    for idx, task in enumerate(tasks):
+        col = idx // 5
+        row = idx % 5
+        x0 = x + 28 + col * col_w
+        y0 = y + 84 + row * row_h
+        proxy = task["task_id"] in PROXY_TASK_IDS
+        color = "#f472b6" if proxy else "#ccffa0"
+        parts.append(f'<rect x="{x0:.1f}" y="{y0 - 17:.1f}" width="35" height="25" rx="6" fill="{color}" fill-opacity="0.13" stroke="{color}" stroke-opacity="0.40"/>')
+        parts.append(svg_text(x0 + 17.5, y0 + 1, f"{task['task_number']:02d}", size=10, fill=color, anchor="middle", weight=850))
+        task_name = str(task["label"])
+        if len(task_name) > 34:
+            task_name = task_name[:31].rstrip() + "..."
+        parts.append(svg_text(x0 + 46, y0 - 2, task_name, size=11 if not compact else 10, fill="#f4f8ef", weight=800))
+        metric = str(task.get("metric_name") or task.get("metric_key") or "")
+        direction = "lower" if task.get("metric_direction") == "lower" else "higher"
+        metric_text = f"{metric}; {direction} better"
+        if proxy:
+            metric_text += "; proxy axis"
+        if len(metric_text) > 43:
+            metric_text = metric_text[:40].rstrip() + "..."
+        parts.append(svg_text(x0 + 46, y0 + 16, metric_text, size=9, fill="#a5afa2", weight=560))
+
+
+def draw_reading_rules(parts: list[str], *, y: float, reading_rules: tuple[str, str, str] | None) -> None:
+    if reading_rules is None:
+        reading_rules = (
+            "Use the panels for shape and coverage; use docs/data/task_method_20_result_matrix.json for exact ranks, raw values, direct/proxy flags, and sources.",
+            "The old nine-method overlay was replaced by grouped small multiples so each radar compares only related methods.",
+            "SVG radius uses sqrt(normalized_score) for readable area; JSON normalized_score remains linear and unchanged.",
+        )
+    parts.append(f'<rect x="70" y="{y:.1f}" width="2260" height="118" rx="14" fill="#020502" fill-opacity="0.62" stroke="#ccffa0" stroke-opacity="0.16"/>')
+    parts.append(svg_text(100, y + 33, "Reading rules", size=16, fill="#ccffa0", weight=850))
+    parts.append(svg_text(230, y + 33, reading_rules[0], size=13, fill="#dce8d7", weight=650))
+    parts.append(svg_text(230, y + 61, reading_rules[1], size=12, fill="#a5afa2", weight=560))
+    parts.append(svg_text(230, y + 87, reading_rules[2], size=12, fill="#a5afa2", weight=560))
+
+
 def render_svg(
     payload: dict[str, Any],
     *,
@@ -1139,29 +1458,27 @@ def render_svg(
     chip_specs: list[tuple[str, str]] | None = None,
     reading_rules: tuple[str, str, str] | None = None,
 ) -> str:
-    width, height = 2400, 1840
-    cx, cy, radius = 650, 860, 355
+    del polygon_series_ids
+    width, height = 2400, 1900
     tasks = payload["tasks"]
-    n = len(tasks)
-    angles = [-math.pi / 2 + 2 * math.pi * i / n for i in range(n)]
     if series_ids is None:
         series_ids = tuple(record["id"] for record in payload["series"])
-    polygon_series_set = set(polygon_series_ids)
-    series_records = [record for record in payload["series"] if record["id"] in set(series_ids)]
+    groups = radar_groups_for_series(series_ids)
+    series_record_by_id = {record["id"]: record for record in payload["series"]}
     parts = [
         f'<svg xmlns="http://www.w3.org/2000/svg" width="{width}" height="{height}" viewBox="0 0 {width} {height}">',
         "<defs>",
-        '<filter id="softGlow"><feGaussianBlur stdDeviation="5" result="blur"/><feMerge><feMergeNode in="blur"/><feMergeNode in="SourceGraphic"/></feMerge></filter>',
-        '<pattern id="dots" width="22" height="22" patternUnits="userSpaceOnUse"><circle cx="2" cy="2" r="1.15" fill="#ccffa0" opacity="0.16"/></pattern>',
+        '<filter id="softGlow"><feGaussianBlur stdDeviation="4" result="blur"/><feMerge><feMergeNode in="blur"/><feMergeNode in="SourceGraphic"/></feMerge></filter>',
+        '<pattern id="dots" width="22" height="22" patternUnits="userSpaceOnUse"><circle cx="2" cy="2" r="1.15" fill="#ccffa0" opacity="0.12"/></pattern>',
         "</defs>",
         '<rect width="100%" height="100%" fill="#020502"/>',
-        '<rect width="100%" height="100%" fill="url(#dots)" opacity="0.45"/>',
-        '<rect x="28" y="28" width="2344" height="1784" rx="18" fill="#061006" fill-opacity="0.88" stroke="#ccffa0" stroke-opacity="0.22"/>',
-        svg_text(70, 86, title or payload.get("title", "20-Task Model Radar"), size=36, weight=800),
+        '<rect width="100%" height="100%" fill="url(#dots)" opacity="0.40"/>',
+        '<rect x="28" y="28" width="2344" height="1844" rx="22" fill="#061006" fill-opacity="0.90" stroke="#ccffa0" stroke-opacity="0.22"/>',
+        svg_text(70, 86, title or payload.get("title", "20-Task Model Radar"), size=36, weight=850),
         svg_text(
             70,
             122,
-            subtitle or "Task names, methods, coverage, and metric normalization in one comparison view.",
+            subtitle or "Grouped small-multiple radars for the nine-method, 180-result comparison.",
             size=18,
             fill="#dce8d7",
             weight=650,
@@ -1170,7 +1487,7 @@ def render_svg(
             70,
             150,
             context_line
-            or "Filled areas show complete scored baselines; colored points show partial branches on task-aligned axes.",
+            or "Related methods are compared in separate panels to avoid the unreadable nine-polygon overlay.",
             size=15,
             fill="#a5afa2",
             weight=560,
@@ -1182,111 +1499,77 @@ def render_svg(
             ("20 task axes", "#ccffa0"),
             (f"{payload['method_task_record_count']} method-task records", "#67e8d1"),
             (f"{payload['scored_method_task_count']} scored records", "#22d3ee"),
-            ("40/40 raw128 pass", "#f59e0b"),
-            ("2 compact proxy records", "#f472b6"),
+            ("grouped small multiples", "#f59e0b"),
+            ("sqrt visual radius", "#f472b6"),
         ]
     chip_x = 70
     for label, color in chip_specs:
-        chip_w = 168 if len(label) < 15 else 250
-        parts.append(f'<rect x="{chip_x}" y="174" width="{chip_w}" height="34" rx="17" fill="{color}" fill-opacity="0.10" stroke="{color}" stroke-opacity="0.38"/>')
-        parts.append(svg_text(chip_x + 16, 197, label, size=13, fill=color, weight=760))
+        chip_w = max(128, min(280, 18 + len(label) * 8.3))
+        parts.append(f'<rect x="{chip_x:.1f}" y="174" width="{chip_w:.1f}" height="34" rx="17" fill="{color}" fill-opacity="0.10" stroke="{color}" stroke-opacity="0.38"/>')
+        parts.append(svg_text(chip_x + 16, 197, label, size=13, fill=color, weight=780))
         chip_x += chip_w + 12
 
-    parts.append('<rect x="54" y="235" width="1190" height="1190" rx="14" fill="#020502" fill-opacity="0.42" stroke="#ccffa0" stroke-opacity="0.14"/>')
-    parts.append(svg_text(84, 276, "Normalized task scores", size=23, weight=800))
-    parts.append(svg_text(84, 302, "Each axis is one task. Longer radius means better after metric-direction normalization.", size=13, fill="#a5afa2", weight=560))
-
-    for level in range(1, 6):
-        r = radius * level / 5
-        ring = [point(cx, cy, r, angle) for angle in angles]
-        parts.append(polyline(ring, fill="none", stroke="#ccffa0", opacity=0, stroke_width=1.1))
-        parts[-1] = parts[-1].replace('fill="none" fill-opacity="0.000"', 'fill="none"').replace('stroke-opacity="0.92"', 'stroke-opacity="0.15"')
-        parts.append(svg_text(cx + 8, cy - r + 4, f"{level / 5:.1f}", size=11, fill="#a5afa2", weight=600, opacity=0.75))
-
-    for task, angle in zip(tasks, angles):
-        x, y = point(cx, cy, radius, angle)
-        parts.append(f'<line x1="{cx:.1f}" y1="{cy:.1f}" x2="{x:.1f}" y2="{y:.1f}" stroke="#ccffa0" stroke-opacity="0.12" stroke-width="1"/>')
-        lx, ly = point(cx, cy, radius + 82, angle)
-        parts.append(f'<circle cx="{lx:.1f}" cy="{ly:.1f}" r="15.5" fill="#ccffa0" fill-opacity="0.12" stroke="#ccffa0" stroke-opacity="0.34"/>')
-        parts.append(svg_text(lx, ly + 4, f"{task['task_number']:02d}", size=11, fill="#ccffa0", anchor="middle", weight=800, opacity=0.98))
-
-    for series_id in series_ids:
-        if series_id not in polygon_series_set:
-            continue
-        spec = SERIES[series_id]
-        points = []
-        for task, angle in zip(tasks, angles):
-            score = task["values"].get(series_id, {}).get("normalized_score")
-            points.append(point(cx, cy, radius * float(score or 0.0), angle))
-        parts.append(polyline(points, fill=spec["color"], stroke=spec["color"], opacity=0.18 if series_id in {"minimal", "raw128_simple"} else 0.16, stroke_width=4.2, dash=spec.get("stroke_dasharray")))
-        for x, y in points:
-            parts.append(f'<circle cx="{x:.1f}" cy="{y:.1f}" r="4.0" fill="{spec["color"]}" stroke="#020502" stroke-width="1.1"/>')
-
-    for series_id in series_ids:
-        if series_id in polygon_series_set:
-            continue
-        spec = SERIES[series_id]
-        for task, angle in zip(tasks, angles):
-            score = task["values"].get(series_id, {}).get("normalized_score")
-            if score is None:
-                continue
-            x, y = point(cx, cy, radius * float(score), angle)
-            radius_px = 6.5 if series_id.startswith(("metadata128", "raw128")) else 8.0
-            parts.append(
-                f'<circle cx="{x:.1f}" cy="{y:.1f}" r="{radius_px:.1f}" fill="{spec["color"]}" fill-opacity="0.92" '
-                f'stroke="#020502" stroke-width="2.0"/>'
+    if len(groups) == 1:
+        draw_radar_panel(
+            parts,
+            x=70,
+            y=242,
+            width=2260,
+            height=1040,
+            group=groups[0],
+            payload=payload,
+            series_record_by_id=series_record_by_id,
+            large=True,
+        )
+        key_y = 1322
+    elif len(groups) == 3:
+        panel_w, panel_h = 1100, 545
+        start_x, start_y = 70, 248
+        gap_x, gap_y = 30, 34
+        for idx, group in enumerate(groups[:2]):
+            draw_radar_panel(
+                parts,
+                x=start_x + idx * (panel_w + gap_x),
+                y=start_y,
+                width=panel_w,
+                height=panel_h,
+                group=group,
+                payload=payload,
+                series_record_by_id=series_record_by_id,
             )
-
-    legend_x, legend_y = 1315, 178
-    parts.append(f'<rect x="{legend_x - 30}" y="{legend_y - 38}" width="1000" height="560" rx="14" fill="#020502" fill-opacity="0.58" stroke="#ccffa0" stroke-opacity="0.20"/>')
-    parts.append(svg_text(legend_x, legend_y, "Methods compared", size=25, weight=800))
-    parts.append(svg_text(legend_x, legend_y + 30, "Each method has 20 records; scores, proxy flags, and sources stay in the JSON matrix.", size=13, fill="#a5afa2", weight=560))
-
-    cursor = legend_y + 74
-    for record in series_records:
-        color = record["color"]
-        parts.append(f'<line x1="{legend_x}" y1="{cursor - 7}" x2="{legend_x + 50}" y2="{cursor - 7}" stroke="{color}" stroke-width="7" stroke-linecap="round"/>')
-        if record["id"] not in polygon_series_set:
-            parts.append(f'<circle cx="{legend_x + 25}" cy="{cursor - 7}" r="7" fill="{color}" stroke="#020502" stroke-width="2"/>')
-        parts.append(svg_text(legend_x + 66, cursor - 12, record["label"], size=15, weight=800))
-        parts.append(svg_text(legend_x + 392, cursor - 12, f"20 records / {record['scored_task_count']} scored", size=13, fill=color, weight=800))
-        detail_lines = split_text(METHOD_DETAILS.get(record["id"], record["scope"]), 78)[:2]
-        parts.extend(svg_text_lines(legend_x + 66, cursor + 8, detail_lines, size=11, fill="#a5afa2", weight=560, line_height=15))
-        cursor += 50
-
-    key_x, key_y = 1315, 780
-    parts.append(f'<rect x="{key_x - 30}" y="{key_y - 44}" width="1000" height="680" rx="14" fill="#020502" fill-opacity="0.58" stroke="#ccffa0" stroke-opacity="0.20"/>')
-    parts.append(svg_text(key_x, key_y, "Task axis key", size=25, weight=800))
-    parts.append(svg_text(key_x, key_y + 30, "Full task names are listed here so the polygon remains readable at homepage scale.", size=13, fill="#a5afa2", weight=560))
-    for idx, task in enumerate(tasks):
-        col = 0 if idx < 10 else 1
-        row = idx if idx < 10 else idx - 10
-        x0 = key_x + col * 500
-        y0 = key_y + 74 + row * 54
-        proxy = task["task_id"] in PROXY_TASK_IDS
-        badge_fill = "#f472b6" if proxy else "#ccffa0"
-        parts.append(f'<rect x="{x0}" y="{y0 - 16}" width="36" height="26" rx="6" fill="{badge_fill}" fill-opacity="0.14" stroke="{badge_fill}" stroke-opacity="0.40"/>')
-        parts.append(svg_text(x0 + 18, y0 + 2, f"{task['task_number']:02d}", size=11, fill=badge_fill, anchor="middle", weight=800))
-        name_lines = split_text(str(task["label"]), 42)[:2]
-        parts.extend(svg_text_lines(x0 + 48, y0 - 3, name_lines, size=12, fill="#f4f8ef", weight=760, line_height=14))
-        metric_label = f"{task.get('metric_name') or task.get('metric_key')} / {'lower better' if task.get('metric_direction') == 'lower' else 'higher better'}"
-        if proxy:
-            metric_label += " / raw128 proxy"
-        parts.append(svg_text(x0 + 48, y0 + 29, metric_label, size=10, fill="#a5afa2", weight=560))
-
-    table_y = 1680
-    if reading_rules is None:
-        reading_rules = (
-            "Every method has 20 task records and the current public matrix scores all 180 rows.",
-            "Raw128 completion: 18 direct task targets plus 2 compact proxies. Task 15 predicts the dominant caption/object/interaction hash bin; task 19 retrieves depth/audio sync from camera pose.",
-            "Proxy flags, raw metric values, and source artifacts stay attached in docs/data/task_method_20_result_matrix.json.",
+        draw_radar_panel(
+            parts,
+            x=start_x,
+            y=start_y + panel_h + gap_y,
+            width=panel_w * 2 + gap_x,
+            height=panel_h,
+            group=groups[2],
+            payload=payload,
+            series_record_by_id=series_record_by_id,
+            large=True,
         )
-    parts.append(f'<rect x="70" y="{table_y - 38}" width="2260" height="120" rx="12" fill="#020502" fill-opacity="0.58" stroke="#ccffa0" stroke-opacity="0.16"/>')
-    parts.append(svg_text(100, table_y - 10, "Reading rules", size=16, fill="#ccffa0", weight=800))
-    parts.append(svg_text(220, table_y - 10, reading_rules[0], size=14, fill="#dce8d7", weight=650))
-    parts.append(svg_text(220, table_y + 18, reading_rules[1], size=13, fill="#a5afa2", weight=560))
-    parts.append(svg_text(220, table_y + 44, reading_rules[2], size=13, fill="#a5afa2", weight=560))
+        key_y = 1438
+    else:
+        panel_w, panel_h = 1100, 545
+        start_x, start_y = 70, 248
+        gap_x, gap_y = 30, 34
+        for idx, group in enumerate(groups):
+            col = idx % 2
+            row = idx // 2
+            draw_radar_panel(
+                parts,
+                x=start_x + col * (panel_w + gap_x),
+                y=start_y + row * (panel_h + gap_y),
+                width=panel_w,
+                height=panel_h,
+                group=group,
+                payload=payload,
+                series_record_by_id=series_record_by_id,
+            )
+        key_y = 1438
 
+    draw_task_key(parts, x=70, y=key_y, width=2260, tasks=tasks, compact=len(groups) == 1)
+    draw_reading_rules(parts, y=1750 if len(groups) > 1 else 1632, reading_rules=reading_rules)
     parts.append("</svg>")
     return "\n".join(parts) + "\n"
 
@@ -1357,8 +1640,8 @@ def main() -> int:
             series_ids=EPISODE128_SERIES,
             polygon_series_ids=("raw128_simple", "raw128_neural_mlp"),
             title="128-Episode 20-Task Radar",
-            subtitle="Selected 96/16/16 episode split; raw-feature heads score all 20 axes.",
-            context_line="Raw128 baselines are filled polygons; metadata, Qwen3, and Cosmos branches now all carry scored task rows.",
+            subtitle="Selected 96/16/16 episode split; all seven 128-episode rows score all 20 axes.",
+            context_line="Metadata, raw-feature, and foundation-model methods are separated into grouped radar panels instead of one crowded overlay.",
             chip_specs=[
                 ("20 task axes", "#ccffa0"),
                 ("140 method-task records", "#67e8d1"),
@@ -1368,7 +1651,7 @@ def main() -> int:
             ],
             reading_rules=(
                 "Every 128-episode method has 20 result records and all 140 rows are scored in this split radar.",
-                "Raw128 Simple and Raw128 NN are complete 20/20 scored multi-episode baselines; tasks 15/19 are documented compact proxies.",
+                "Raw128 Simple and Raw128 NN are complete 20/20 scored multi-episode baselines; tasks 15/19 are documented compact proxies and are marked in the task key.",
                 "Qwen3-Omni and Cosmos3 rows use verified held-out outputs or derived probe artifacts; source paths stay in the matrix JSON.",
             ),
         ),