Add files using upload-large-folder tool

TASK_METHOD_20_GAP_AUDIT.md

@@ -1,6 +1,6 @@
 # Task Method 20-Result Gap Audit
 
-Generated: `2026-06-18T11:15:34+00:00`
+Generated: `2026-06-18T12:07:14+00:00`
 
 This audit is the explicit gap ledger for the 9-method x 20-task result matrix.
 It keeps missing cells visible while preserving the rule that a numeric score
@@ -9,8 +9,8 @@ requires a real task target and source artifact.
 ## Score Summary
 
 - Method-task records: `180`
-- Numeric scored records: `123`
-- Scoreless records: `57`
+- Numeric scored records: `127`
+- Scoreless records: `53`
 - Proxy-scored records: `4`
 - Source matrix: [`docs/data/task_method_20_result_matrix.json`](docs/data/task_method_20_result_matrix.json)
 
@@ -20,8 +20,8 @@ requires a real task target and source artifact.
 | --- | --- | --- | --- | --- | --- |
 | Minimal | minimal | 20/20 | 0 | 0 | scored: 20 |
 | Neural MLP | neural_mlp | 20/20 | 0 | 0 | scored: 20 |
-| 128ep Metadata Simple | metadata128_simple | 8/20 | 12 | 0 | not_supported_by_metadata_only_package: 8, scored: 8, unsupported_without_required_target: 4 |
-| 128ep Metadata NN | metadata128_neural_mlp | 8/20 | 12 | 0 | not_supported_by_metadata_only_package: 12, scored: 8 |
+| 128ep Metadata Simple | metadata128_simple | 13/20 | 7 | 0 | scored: 13, unsupported_without_required_target: 7 |
+| 128ep Metadata NN | metadata128_neural_mlp | 7/20 | 13 | 0 | not_supported_by_metadata_only_package: 7, scored: 7, unsupported_without_required_target: 6 |
 | 128ep Raw Simple | raw128_simple | 20/20 | 0 | 2 | proxy_scored: 2, scored: 18 |
 | 128ep Raw NN | raw128_neural_mlp | 20/20 | 0 | 2 | proxy_scored: 2, scored: 18 |
 | Qwen3-Omni v6 LoRA | qwen3_omni_v6_lora | 15/20 | 5 | 0 | not_evaluated_in_verified_package: 5, scored: 15 |
@@ -33,14 +33,17 @@ requires a real task target and source artifact.
 | Status | Count | Next step |
 | --- | --- | --- |
 | not_evaluated_in_verified_package | 33 | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| not_supported_by_metadata_only_package | 20 | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
-| unsupported_without_required_target | 4 | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
+| not_supported_by_metadata_only_package | 7 | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
+| unsupported_without_required_target | 13 | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 
 ## Scoreless Records
 
 | Task | Task label | Method | Status | Required evidence |
 | --- | --- | --- | --- | --- |
+| 01 | Action Recognition | 128ep Metadata NN | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
+| 02 | Procedure Step Recognition | 128ep Metadata NN | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 02 | Procedure Step Recognition | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
+| 04 | Next-Action Prediction | 128ep Metadata NN | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 05 | Hand Trajectory Forecasting | 128ep Metadata Simple | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 05 | Hand Trajectory Forecasting | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
 | 05 | Hand Trajectory Forecasting | Qwen3-Omni v6 LoRA | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
@@ -63,38 +66,31 @@ requires a real task target and source artifact.
 | 12 | Multimodal Synchronization Detection | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
 | 12 | Multimodal Synchronization Detection | Cosmos3-Super Reasoner | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 12 | Multimodal Synchronization Detection | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| 13 | Long-Horizon Next-Action Forecasting | 128ep Metadata Simple | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
-| 13 | Long-Horizon Next-Action Forecasting | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
+| 13 | Long-Horizon Next-Action Forecasting | 128ep Metadata NN | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 13 | Long-Horizon Next-Action Forecasting | Cosmos3-Super Reasoner | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 13 | Long-Horizon Next-Action Forecasting | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| 14 | Long-Horizon Next-Subtask Forecasting | 128ep Metadata Simple | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
-| 14 | Long-Horizon Next-Subtask Forecasting | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
+| 14 | Long-Horizon Next-Subtask Forecasting | 128ep Metadata NN | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 14 | Long-Horizon Next-Subtask Forecasting | Cosmos3-Super Reasoner | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 14 | Long-Horizon Next-Subtask Forecasting | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| 15 | Interaction Text Prediction | 128ep Metadata Simple | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
+| 15 | Interaction Text Prediction | 128ep Metadata Simple | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 15 | Interaction Text Prediction | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
 | 15 | Interaction Text Prediction | Qwen3-Omni v6 LoRA | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 15 | Interaction Text Prediction | Cosmos3-Super Reasoner | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 15 | Interaction Text Prediction | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| 16 | Action-Object Relation Prediction | 128ep Metadata Simple | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
-| 16 | Action-Object Relation Prediction | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
+| 16 | Action-Object Relation Prediction | 128ep Metadata NN | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 16 | Action-Object Relation Prediction | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| 17 | Future Object-Set Forecasting | 128ep Metadata Simple | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
-| 17 | Future Object-Set Forecasting | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
 | 17 | Future Object-Set Forecasting | Cosmos3-Super Reasoner | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 17 | Future Object-Set Forecasting | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| 18 | IMU-to-Hand Pose Reconstruction | 128ep Metadata Simple | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
+| 18 | IMU-to-Hand Pose Reconstruction | 128ep Metadata Simple | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 18 | IMU-to-Hand Pose Reconstruction | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
 | 18 | IMU-to-Hand Pose Reconstruction | Qwen3-Omni v6 LoRA | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 18 | IMU-to-Hand Pose Reconstruction | Cosmos3-Super Reasoner | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 18 | IMU-to-Hand Pose Reconstruction | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| 19 | Camera-View Synchronization Retrieval | 128ep Metadata Simple | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
+| 19 | Camera-View Synchronization Retrieval | 128ep Metadata Simple | unsupported | Export the missing target field for this 128-episode method, then rerun the same train/validation/test split. |
 | 19 | Camera-View Synchronization Retrieval | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
 | 19 | Camera-View Synchronization Retrieval | Qwen3-Omni v6 LoRA | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 19 | Camera-View Synchronization Retrieval | Cosmos3-Super Reasoner | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 19 | Camera-View Synchronization Retrieval | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
-| 20 | Time-to-Next-Transition Regression | 128ep Metadata Simple | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
-| 20 | Time-to-Next-Transition Regression | 128ep Metadata NN | not supported | Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score. |
 | 20 | Time-to-Next-Transition Regression | Cosmos3-Super Reasoner | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 | 20 | Time-to-Next-Transition Regression | Cosmos3-Nano Future Window | not evaluated | Generate verified model outputs for this task contract and score them against the held-out labels. |
 

TASK_METHOD_20_RESULT_MATRIX.md

@@ -8,8 +8,8 @@ Legend: `score` = numeric task score, `proxy` = documented raw128 compact proxy
 | --- | ---: | ---: | ---: | ---: | --- |
 | Minimal | 20 | 20 | 0 | 0 | scored 20 |
 | Neural MLP | 20 | 20 | 0 | 0 | scored 20 |
-| 128ep Metadata Simple | 20 | 8 | 0 | 12 | not supported 8, scored 8, unsupported 4 |
-| 128ep Metadata NN | 20 | 8 | 0 | 12 | not supported 12, scored 8 |
+| 128ep Metadata Simple | 20 | 13 | 0 | 7 | scored 13, unsupported 7 |
+| 128ep Metadata NN | 20 | 13 | 0 | 7 | not supported 7, scored 13 |
 | 128ep Raw Simple | 20 | 20 | 2 | 0 | proxy scored 2, scored 18 |
 | 128ep Raw NN | 20 | 20 | 2 | 0 | proxy scored 2, scored 18 |
 | Qwen3-Omni v6 LoRA | 20 | 15 | 0 | 5 | not evaluated 5, scored 15 |
@@ -30,13 +30,13 @@ Legend: `score` = numeric task score, `proxy` = documented raw128 compact proxy
 | 10 | Cross-Modal Reconstruction | score | score | unsupported | not supported | score | score | not evaluated | not evaluated | not evaluated |
 | 11 | Temporal Order Verification | score | score | score | score | score | score | score | not evaluated | not evaluated |
 | 12 | Multimodal Synchronization Detection | score | score | unsupported | not supported | score | score | score | not evaluated | not evaluated |
-| 13 | Long-Horizon Next-Action Forecasting | score | score | not supported | not supported | score | score | score | not evaluated | not evaluated |
-| 14 | Long-Horizon Next-Subtask Forecasting | score | score | not supported | not supported | score | score | score | not evaluated | not evaluated |
-| 15 | Interaction Text Prediction | score | score | not supported | not supported | proxy | proxy | not evaluated | not evaluated | not evaluated |
-| 16 | Action-Object Relation Prediction | score | score | not supported | not supported | score | score | score | score | not evaluated |
-| 17 | Future Object-Set Forecasting | score | score | not supported | not supported | score | score | score | not evaluated | not evaluated |
-| 18 | IMU-to-Hand Pose Reconstruction | score | score | not supported | not supported | score | score | not evaluated | not evaluated | not evaluated |
-| 19 | Camera-View Synchronization Retrieval | score | score | not supported | not supported | proxy | proxy | not evaluated | not evaluated | not evaluated |
-| 20 | Time-to-Next-Transition Regression | score | score | not supported | not supported | score | score | score | not evaluated | not evaluated |
+| 13 | Long-Horizon Next-Action Forecasting | score | score | score | score | score | score | score | not evaluated | not evaluated |
+| 14 | Long-Horizon Next-Subtask Forecasting | score | score | score | score | score | score | score | not evaluated | not evaluated |
+| 15 | Interaction Text Prediction | score | score | unsupported | not supported | proxy | proxy | not evaluated | not evaluated | not evaluated |
+| 16 | Action-Object Relation Prediction | score | score | score | score | score | score | score | score | not evaluated |
+| 17 | Future Object-Set Forecasting | score | score | score | score | score | score | score | not evaluated | not evaluated |
+| 18 | IMU-to-Hand Pose Reconstruction | score | score | unsupported | not supported | score | score | not evaluated | not evaluated | not evaluated |
+| 19 | Camera-View Synchronization Retrieval | score | score | unsupported | not supported | proxy | proxy | not evaluated | not evaluated | not evaluated |
+| 20 | Time-to-Next-Transition Regression | score | score | score | score | score | score | score | not evaluated | not evaluated |
 
 Sources and raw values are in `docs/data/task_method_20_result_matrix.json` and `docs/data/unified_task_model_radar.json`.

data/artifact_index.json

@@ -1,6 +1,6 @@
 {
   "title": "Ropedia Xperience-10M Task Suite Artifact Index",
-  "generated_at_utc": "2026-06-18T11:16:44+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+00:00",
   "status": "pass",
   "artifact_count": 213,
   "missing": [],
@@ -290,8 +290,8 @@
       "surface": "repo_hf",
       "shows": "Runs simple metadata and neural MLP baselines on the same selected 96/16/16 episode split used by the Qwen3-Omni diagnostic pilot.",
       "exists": true,
-      "bytes": 58012,
-      "sha256": "a95cdde097b11f83023c758c807f031c3d4cb3fde20d42ed314565440cc68374"
+      "bytes": 73236,
+      "sha256": "76acae0de25d51413e7e6f11021163e7d9909cfe95d65bf6b02e74043d429e2d"
     },
     {
       "id": "task_suite_enhancement_128",
@@ -599,7 +599,7 @@
       "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
       "exists": true,
       "bytes": 4432,
-      "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
+      "sha256": "ae089cc0df132b63365e03b2157a488b5d1569567c0374d7621bcd347da62c9e"
     },
     {
       "id": "source_alignment_validator",
@@ -719,8 +719,8 @@
       "surface": "website_hf",
       "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3/Cosmos overlay mappings, branch-card caveats, and explicit scoreless status records.",
       "exists": true,
-      "bytes": 230951,
-      "sha256": "8aaed21d08943f2dc53c5160e27872bc4f7f8a405d7289cdaaf7b00d867b84d8"
+      "bytes": 230297,
+      "sha256": "437874b1633e73165e3300f55580394663a44759c848288e696859b98f8aad32"
     },
     {
       "id": "single_episode_task_model_radar_json",
@@ -731,7 +731,7 @@
       "shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
       "exists": true,
       "bytes": 50973,
-      "sha256": "d20637e6a17390f7fd44589ff37cb1889318bc39c2259dca6bb7f1a43d8ea26b"
+      "sha256": "38cb43512f2ac40feeb62333bdea89b3a55e5b48468beb8982cf22536f794ecf"
     },
     {
       "id": "episode128_task_model_radar_json",
@@ -741,8 +741,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines and verified Qwen3/Cosmos branches, preserving explicit scoreless cells.",
       "exists": true,
-      "bytes": 187099,
-      "sha256": "bf2b3fdeb9713a9d4cba0e8645c24c325b88e939cb94f4718a9d3c2db03e2bb3"
+      "bytes": 186443,
+      "sha256": "55e758e8703f406889022976d0ba055181212305c9a7246e899463e0c3c3b554"
     },
     {
       "id": "task_method_20_result_matrix_json",
@@ -752,8 +752,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and scoreless cells carry unsupported/not-evaluated reasons.",
       "exists": true,
-      "bytes": 129600,
-      "sha256": "30fd572521991fd7f5741411d91a40d3d442032f001841f9fd1a4e7381eb73d2"
+      "bytes": 129242,
+      "sha256": "64fb700d51f536edf11291799b6173cf9ae8dd7a41178aac348b8207ed4b1e42"
     },
     {
       "id": "task_method_20_result_matrix",
@@ -763,8 +763,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing table that separates 20 records per method from numeric scored axes, documented raw128 proxy scores, unsupported metadata targets, and model targets not evaluated in verified packages.",
       "exists": true,
-      "bytes": 4128,
-      "sha256": "89c73da7db81d2c5f6eb4a16c828531a589ac44cabba2c0c95b171b6ad2060d6"
+      "bytes": 4026,
+      "sha256": "55e949fc30419a52f7f5ec4dd9544a11b253b076f8e3637ec3e92b3d61a89aab"
     },
     {
       "id": "task_method_20_gap_audit_json",
@@ -774,8 +774,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 180-record gap ledger with numeric scores, scoreless cells, explicit status reasons, and next evidence needed before new scores can be published.",
       "exists": true,
-      "bytes": 50687,
-      "sha256": "2cdaa06f9c140a2e194675a3383be341acb1f6e07ddecfa7017cdbe34d704282"
+      "bytes": 46902,
+      "sha256": "2b64dbd013625852679f9b91d25c48d1ed197fec727883b4fe37088b2d594784"
     },
     {
       "id": "task_method_20_gap_audit",
@@ -785,8 +785,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing ledger that lists every scoreless method-task cell and the concrete target or model-output evidence required before it can become numeric.",
       "exists": true,
-      "bytes": 14421,
-      "sha256": "125e658010284dc48570fa7c6a7676e4013d30dd1f22deb24d369e7085a7b700"
+      "bytes": 13387,
+      "sha256": "d33461eb704f8e92545b6b54d9fc509e617fbacc9ca9894ac851ca9c3dec0fec"
     },
     {
       "id": "unified_task_model_radar_chart",
@@ -796,8 +796,8 @@
       "surface": "website_hf",
       "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3/Cosmos task-aligned model overlays.",
       "exists": true,
-      "bytes": 50841,
-      "sha256": "e5fa2420fc5ed905953e71ef8978ad1ee794c0daf06a7f0ff10374db7f291c72"
+      "bytes": 51953,
+      "sha256": "19c001f10319946ef0e4921064f8a012836f29e7c8b272f900c257169faf46a1"
     },
     {
       "id": "single_episode_task_model_radar_chart",
@@ -818,8 +818,8 @@
       "surface": "website_hf",
       "shows": "Separates the selected 128-episode methods: raw-feature simple/NN as complete 20/20 scored polygons and metadata/Qwen/Cosmos as task-aligned overlays.",
       "exists": true,
-      "bytes": 44825,
-      "sha256": "50b5d87fca4aba303a8440f5ef53470ed493e9f1251cb5edeb16bac90038a11b"
+      "bytes": 45937,
+      "sha256": "b504b1b9c5cad0caa8c822d5bb2971c1b708251cf7b9ef587a92db2c12751e97"
     },
     {
       "id": "unified_task_model_radar_builder",
@@ -906,8 +906,8 @@
       "surface": "repo_hf",
       "shows": "Rerun of JSONL metadata/text simple and neural baselines over the selected 128-episode multiscale dataset; supports radar overlays on JSONL-supported task axes.",
       "exists": true,
-      "bytes": 50297,
-      "sha256": "1c1710bcf340ece479e321f19d4cb8302fe369a1103b4584a15853fe73dc226c"
+      "bytes": 109248,
+      "sha256": "5e7f3085be5012eb3dda46f9c7b5b7c0ae22d6a0fbce71d6e99dd317fecc12af"
     },
     {
       "id": "a100_128_raw20_task_baselines",
@@ -1105,7 +1105,7 @@
       "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
       "exists": true,
       "bytes": 8100,
-      "sha256": "6549b0f8da6c3742c72b12b71900db1b89455cd34d5befcdf9d249b4adebbd1a"
+      "sha256": "7800195093b8b81b49c87cdcbcebe601de8141c0c9d8b4490b98f539cb132725"
     },
     {
       "id": "public_surface_qa",
@@ -1310,7 +1310,7 @@
       "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": 983979,
+      "bytes": 994053,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1322,7 +1322,7 @@
       "volatile": true,
       "shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
       "exists": true,
-      "bytes": 20022,
+      "bytes": 20021,
       "hash_policy": "existence_and_size_only"
     },
     {

data/episode128_task_model_radar.json

@@ -1,12 +1,12 @@
 {
   "title": "128-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3/Cosmos branches. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.",
   "task_count": 20,
   "method_count": 7,
   "method_task_record_count": 140,
-  "scored_method_task_count": 83,
+  "scored_method_task_count": 93,
   "normalization_policy": {
     "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
     "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -30,18 +30,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -55,17 +54,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -1295,26 +1294,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.004579592783699693,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.004579592783699693,
+          "raw_text": "0.0046",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.0029821307969142615,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0029821307969142615,
+          "raw_text": "0.0030",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0024280172369056294,
@@ -1386,26 +1385,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.0001206030150753769,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0001206030150753769,
+          "raw_text": "0.0001",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 2.086049543676662e-05,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 2.086049543676662e-05,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0,
@@ -1479,13 +1478,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1568,26 +1567,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.0,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.0,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0,
@@ -1659,26 +1658,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.17656983343047333,
           "metric_key": "micro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17656983343047333,
+          "raw_text": "0.1766",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.17418550827844048,
           "metric_key": "micro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17418550827844048,
+          "raw_text": "0.1742",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.06469493412657774,
@@ -1752,13 +1751,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1843,13 +1842,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "mrr",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1932,26 +1931,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 624.8108520507812,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.016864874132806403,
+          "raw_text": "624.81",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 41.4664421081543,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.25411768748242325,
+          "raw_text": "41.47",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 52.32759475708008,
@@ -3530,17 +3529,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -3548,17 +3547,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -3656,17 +3655,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -3674,17 +3673,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -3782,17 +3781,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -3908,17 +3907,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -3926,17 +3925,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -4034,17 +4033,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -4052,17 +4051,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -4160,17 +4159,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -4286,17 +4285,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -4412,17 +4411,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -4430,17 +4429,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

data/public_surface_qa.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Public Project Surface",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:41:42+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+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": "2026-06-18T11:18:05+00:00"
+          "generated_at_utc": "2026-06-18T11:41:43+00:00"
         },
         "rendered_site_check": {
           "exists": true,
@@ -43,12 +43,12 @@
         "publication_package": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-18T11:18:57+00:00"
+          "generated_at_utc": "2026-06-18T11:42:48+00:00"
         },
         "mirror_parity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-18T11:21:54+00:00"
+          "generated_at_utc": "2026-06-18T11:43:59+00:00"
         }
       },
       "failures": {}

data/publication_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:42:48+00:00",
+  "generated_at_utc": "2026-06-18T12:10:47+00:00",
   "checks": [
     {
       "name": "required_publication_assets_present",
@@ -215,8 +215,8 @@
     "github_repo": {
       "root": "repo",
       "exists": true,
-      "file_count": 1276,
-      "text_file_count": 1072,
+      "file_count": 1321,
+      "text_file_count": 1108,
       "largest_file": {
         "path": "results/episode_task_suite/modality_reconstruction/predictions.npz",
         "bytes": 55702978
@@ -226,8 +226,8 @@
     "hf_space_bundle": {
       "root": "hf_publish/space",
       "exists": true,
-      "file_count": 1058,
-      "text_file_count": 879,
+      "file_count": 1103,
+      "text_file_count": 915,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061
@@ -237,8 +237,8 @@
     "hf_artifact_bundle": {
       "root": "hf_publish/artifacts",
       "exists": true,
-      "file_count": 2537,
-      "text_file_count": 1085,
+      "file_count": 2582,
+      "text_file_count": 1121,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061
@@ -248,8 +248,8 @@
     "hf_model_bundle": {
       "root": "hf_publish/model",
       "exists": true,
-      "file_count": 2956,
-      "text_file_count": 1247,
+      "file_count": 3001,
+      "text_file_count": 1283,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061

data/quality_gates.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Release Checks",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:20:56+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+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": [
     {

data/scope_claims_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:18:06+00:00",
+  "generated_at_utc": "2026-06-18T12:09:48+00:00",
   "summary": {
     "qwen3_omni_verified_diagnostic_pilot": true,
     "dataset_manifest_num_episodes": 119,

data/single_episode_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "Single-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+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,

data/source_alignment_audit.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Source Alignment Note",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:18:04+00:00",
+  "generated_at_utc": "2026-06-18T12:09:45+00:00",
   "alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
   "alignment_summary": {
     "full_dataset_repo": "ropedia-ai/xperience-10m",

data/task_method_20_gap_audit.json

@@ -1,10 +1,10 @@
 {
-  "generated_at_utc": "2026-06-18T11:15:34+00:00",
+  "generated_at_utc": "2026-06-18T12:07:14+00:00",
   "immediate_actions": [
     {
       "artifact": "docs/data/task_method_20_gap_audit.json",
       "id": "gap_audit",
-      "purpose": "Keep the 57 scoreless cells visible and reproducible."
+      "purpose": "Keep the 53 scoreless cells visible and reproducible."
     },
     {
       "artifact": "scripts/omni/score_model_output_probes.py",
@@ -50,11 +50,12 @@
       "proxy_scored_task_count": 0,
       "result_record_count": 20,
       "scope": "128 selected episodes, JSONL metadata/text only",
-      "scored_task_count": 8,
-      "scoreless_task_count": 12,
+      "scored_task_count": 7,
+      "scoreless_task_count": 13,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 7,
+        "unsupported_without_required_target": 6
       }
     },
     "metadata128_simple": {
@@ -63,12 +64,11 @@
       "proxy_scored_task_count": 0,
       "result_record_count": 20,
       "scope": "128 selected episodes, JSONL metadata/text only",
-      "scored_task_count": 8,
-      "scoreless_task_count": 12,
+      "scored_task_count": 13,
+      "scoreless_task_count": 7,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       }
     },
     "minimal": {
@@ -138,18 +138,25 @@
   "missing_by_method": {
     "cosmos3_nano_future_window": 15,
     "cosmos3_super_reasoner": 13,
-    "metadata128_neural_mlp": 12,
-    "metadata128_simple": 12,
+    "metadata128_neural_mlp": 13,
+    "metadata128_simple": 7,
     "qwen3_omni_v6_lora": 5
   },
   "missing_by_status": {
     "not_evaluated_in_verified_package": 33,
-    "not_supported_by_metadata_only_package": 20,
-    "unsupported_without_required_target": 4
+    "not_supported_by_metadata_only_package": 7,
+    "unsupported_without_required_target": 13
   },
   "missing_by_task": {
+    "01 Action Recognition": [
+      "metadata128_neural_mlp"
+    ],
     "02 Procedure Step Recognition": [
-      "cosmos3_nano_future_window"
+      "cosmos3_nano_future_window",
+      "metadata128_neural_mlp"
+    ],
+    "04 Next-Action Prediction": [
+      "metadata128_neural_mlp"
     ],
     "05 Hand Trajectory Forecasting": [
       "cosmos3_nano_future_window",
@@ -190,14 +197,12 @@
     "13 Long-Horizon Next-Action Forecasting": [
       "cosmos3_nano_future_window",
       "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "14 Long-Horizon Next-Subtask Forecasting": [
       "cosmos3_nano_future_window",
       "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "15 Interaction Text Prediction": [
       "cosmos3_nano_future_window",
@@ -208,14 +213,11 @@
     ],
     "16 Action-Object Relation Prediction": [
       "cosmos3_nano_future_window",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "17 Future Object-Set Forecasting": [
       "cosmos3_nano_future_window",
-      "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "cosmos3_super_reasoner"
     ],
     "18 IMU-to-Hand Pose Reconstruction": [
       "cosmos3_nano_future_window",
@@ -233,12 +235,36 @@
     ],
     "20 Time-to-Next-Transition Regression": [
       "cosmos3_nano_future_window",
-      "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "cosmos3_super_reasoner"
     ]
   },
   "missing_records": [
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 896 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "timeline_action",
+      "task_label": "Action Recognition",
+      "task_number": 1
+    },
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 652 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "timeline_subtask",
+      "task_label": "Procedure Step Recognition",
+      "task_number": 2
+    },
     {
       "method": "Cosmos3-Nano Future Window",
       "metric_key": "macro_f1",
@@ -252,6 +278,19 @@
       "task_label": "Procedure Step Recognition",
       "task_number": 2
     },
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 891 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "next_action",
+      "task_label": "Next-Action Prediction",
+      "task_number": 4
+    },
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mpjpe",
@@ -538,28 +577,15 @@
       "task_label": "Multimodal Synchronization Detection",
       "task_number": 12
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "long_horizon_next_action",
-      "task_label": "Long-Horizon Next-Action Forecasting",
-      "task_number": 13
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 887 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "long_horizon_next_action",
       "task_label": "Long-Horizon Next-Action Forecasting",
       "task_number": 13
@@ -590,28 +616,15 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "task_number": 13
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "next_subtask_forecast",
-      "task_label": "Long-Horizon Next-Subtask Forecasting",
-      "task_number": 14
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 651 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "next_subtask_forecast",
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "task_number": 14
@@ -645,12 +658,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "interaction_text_prediction",
       "task_label": "Interaction Text Prediction",
       "task_number": 15
@@ -707,28 +720,15 @@
       "task_label": "Interaction Text Prediction",
       "task_number": 15
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "action_object_relation",
-      "task_label": "Action-Object Relation Prediction",
-      "task_number": 16
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 3058 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "action_object_relation",
       "task_label": "Action-Object Relation Prediction",
       "task_number": 16
@@ -746,32 +746,6 @@
       "task_label": "Action-Object Relation Prediction",
       "task_number": 16
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "micro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "object_set_forecast",
-      "task_label": "Future Object-Set Forecasting",
-      "task_number": 17
-    },
-    {
-      "method": "128ep Metadata NN",
-      "metric_key": "micro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "object_set_forecast",
-      "task_label": "Future Object-Set Forecasting",
-      "task_number": 17
-    },
     {
       "method": "Cosmos3-Super Reasoner",
       "metric_key": "micro_f1",
@@ -801,12 +775,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "imu_to_hand_pose",
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "task_number": 18
@@ -866,12 +840,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mrr",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "camera_view_sync_retrieval",
       "task_label": "Camera-View Synchronization Retrieval",
       "task_number": 19
@@ -928,32 +902,6 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "task_number": 19
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "time_to_transition",
-      "task_label": "Time-to-Next-Transition Regression",
-      "task_number": 20
-    },
-    {
-      "method": "128ep Metadata NN",
-      "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "time_to_transition",
-      "task_label": "Time-to-Next-Transition Regression",
-      "task_number": 20
-    },
     {
       "method": "Cosmos3-Super Reasoner",
       "metric_key": "mae",
@@ -1027,8 +975,8 @@
     "method_count": 9,
     "method_task_record_count": 180,
     "proxy_scored_method_task_count": 4,
-    "scored_method_task_count": 123,
-    "scoreless_method_task_count": 57,
+    "scored_method_task_count": 127,
+    "scoreless_method_task_count": 53,
     "task_count": 20
   },
   "source_matrix": "docs/data/task_method_20_result_matrix.json",

data/task_method_20_result_matrix.json

@@ -1,11 +1,11 @@
 {
   "title": "Task Method 20-Result Matrix",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
-  "scored_method_task_count": 123,
+  "scored_method_task_count": 133,
   "series": [
     {
       "id": "minimal",
@@ -64,18 +64,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -89,17 +88,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -2210,17 +2209,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -2228,17 +2227,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -2372,17 +2371,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -2390,17 +2389,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -2534,17 +2533,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -2696,17 +2695,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -2714,17 +2713,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -2858,17 +2857,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -2876,17 +2875,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -3020,17 +3019,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -3182,17 +3181,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -3344,17 +3343,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -3362,17 +3361,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

data/task_surface_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:18:04+00:00",
+  "generated_at_utc": "2026-06-18T12:09:25+00:00",
   "summary": {
     "task_count": 12,
     "expected_task_count": 12,

data/unified_task_model_radar.json

@@ -1,11 +1,11 @@
 {
   "title": "Unified 20-Task Model Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
-  "scored_method_task_count": 123,
+  "scored_method_task_count": 133,
   "normalization_policy": {
     "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
     "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -73,18 +73,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -98,17 +97,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -1608,6 +1607,28 @@
           "raw_text": "0.0023",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.004579592783699693,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.004579592783699693,
+          "raw_text": "0.0046",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.0029821307969142615,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0029821307969142615,
+          "raw_text": "0.0030",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0024280172369056294,
           "metric_key": "macro_f1",
@@ -1630,28 +1651,6 @@
           "raw_text": "0.0011",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1719,6 +1718,28 @@
           "raw_text": "0.0042",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.0001206030150753769,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0001206030150753769,
+          "raw_text": "0.0001",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 2.086049543676662e-05,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 2.086049543676662e-05,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0,
           "metric_key": "macro_f1",
@@ -1741,28 +1762,6 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1819,6 +1818,17 @@
           "raw_text": "0.0381",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.012611998261547169,
           "metric_key": "macro_f1",
@@ -1841,17 +1851,6 @@
           "raw_text": "0.0098",
           "status_label": "proxy scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1952,6 +1951,28 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.0,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.0,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0,
           "metric_key": "macro_f1",
@@ -1974,28 +1995,6 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_nano_future_window": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -2052,6 +2051,28 @@
           "raw_text": "0.1659",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.17656983343047333,
+          "metric_key": "micro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17656983343047333,
+          "raw_text": "0.1766",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.17418550827844048,
+          "metric_key": "micro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17418550827844048,
+          "raw_text": "0.1742",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.06469493412657774,
           "metric_key": "micro_f1",
@@ -2074,28 +2095,6 @@
           "raw_text": "0.1752",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "micro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "micro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "micro_f1",
@@ -2152,6 +2151,17 @@
           "raw_text": "0.0426",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.22941437363624573,
           "metric_key": "mae",
@@ -2174,17 +2184,6 @@
           "raw_text": "0.2530",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "mae",
@@ -2263,6 +2262,17 @@
           "raw_text": "0.2409",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "mrr",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.0026625150348991156,
           "metric_key": "mrr",
@@ -2285,17 +2295,6 @@
           "raw_text": "0.0025",
           "status_label": "proxy scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mrr",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "mrr",
@@ -2385,6 +2384,28 @@
           "raw_text": "134.07",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 624.8108520507812,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.016864874132806403,
+          "raw_text": "624.81",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 41.4664421081543,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.25411768748242325,
+          "raw_text": "41.47",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 52.32759475708008,
           "metric_key": "mae",
@@ -2407,28 +2428,6 @@
           "raw_text": "42.37",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "mae",
@@ -2459,7 +2458,7 @@
       "id": "metadata128_simple",
       "title": "128ep Metadata Simple",
       "status": "a100_rerun_pass",
-      "coverage": "20 records / 8 scored JSONL-supported axes",
+      "coverage": "20 records / 13 scored JSONL-supported axes",
       "headline": "34,269 rows; train/val/test 25,629/4,608/4,032",
       "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/summary_report.json"
     },
@@ -2467,7 +2466,7 @@
       "id": "metadata128_neural_mlp",
       "title": "128ep Metadata NN",
       "status": "a100_rerun_pass",
-      "coverage": "20 records / 8 scored JSONL-supported axes",
+      "coverage": "20 records / 13 scored JSONL-supported axes",
       "headline": "compact MLP heads over metadata/text features",
       "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/summary_report.json"
     },
@@ -4508,17 +4507,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -4526,17 +4525,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -4670,17 +4669,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -4688,17 +4687,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -4832,17 +4831,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -4994,17 +4993,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -5012,17 +5011,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -5156,17 +5155,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -5174,17 +5173,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -5318,17 +5317,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -5480,17 +5479,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -5642,17 +5641,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -5660,17 +5659,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

data/website_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:41:43+00:00",
+  "generated_at_utc": "2026-06-18T12:09:46+00:00",
   "docs_root": "docs",
   "site_base": "/ropedia-xperience-10m-task-suite/",
   "summary": {
@@ -301,7 +301,7 @@
     },
     {
       "path": "data/artifact_index.json",
-      "bytes": 116109,
+      "bytes": 116110,
       "top_level_type": "dict"
     },
     {
@@ -316,7 +316,7 @@
     },
     {
       "path": "data/episode128_task_model_radar.json",
-      "bytes": 187099,
+      "bytes": 186443,
       "top_level_type": "dict"
     },
     {
@@ -486,12 +486,12 @@
     },
     {
       "path": "data/task_method_20_gap_audit.json",
-      "bytes": 50687,
+      "bytes": 46902,
       "top_level_type": "dict"
     },
     {
       "path": "data/task_method_20_result_matrix.json",
-      "bytes": 129600,
+      "bytes": 129242,
       "top_level_type": "dict"
     },
     {
@@ -526,7 +526,7 @@
     },
     {
       "path": "data/unified_task_model_radar.json",
-      "bytes": 230951,
+      "bytes": 230297,
       "top_level_type": "dict"
     },
     {
@@ -571,7 +571,7 @@
     {
       "path": "assets/charts/episode128_task_model_radar.svg",
       "exists": true,
-      "bytes": 44825,
+      "bytes": 45937,
       "format": "SVG",
       "has_viewbox": true
     },
@@ -641,7 +641,7 @@
     {
       "path": "assets/charts/unified_task_model_radar.svg",
       "exists": true,
-      "bytes": 50841,
+      "bytes": 51953,
       "format": "SVG",
       "has_viewbox": true
     },

docs/data/artifact_index.json

@@ -1,6 +1,6 @@
 {
   "title": "Ropedia Xperience-10M Task Suite Artifact Index",
-  "generated_at_utc": "2026-06-18T11:16:44+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+00:00",
   "status": "pass",
   "artifact_count": 213,
   "missing": [],
@@ -290,8 +290,8 @@
       "surface": "repo_hf",
       "shows": "Runs simple metadata and neural MLP baselines on the same selected 96/16/16 episode split used by the Qwen3-Omni diagnostic pilot.",
       "exists": true,
-      "bytes": 58012,
-      "sha256": "a95cdde097b11f83023c758c807f031c3d4cb3fde20d42ed314565440cc68374"
+      "bytes": 73236,
+      "sha256": "76acae0de25d51413e7e6f11021163e7d9909cfe95d65bf6b02e74043d429e2d"
     },
     {
       "id": "task_suite_enhancement_128",
@@ -599,7 +599,7 @@
       "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
       "exists": true,
       "bytes": 4432,
-      "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
+      "sha256": "ae089cc0df132b63365e03b2157a488b5d1569567c0374d7621bcd347da62c9e"
     },
     {
       "id": "source_alignment_validator",
@@ -719,8 +719,8 @@
       "surface": "website_hf",
       "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3/Cosmos overlay mappings, branch-card caveats, and explicit scoreless status records.",
       "exists": true,
-      "bytes": 230951,
-      "sha256": "8aaed21d08943f2dc53c5160e27872bc4f7f8a405d7289cdaaf7b00d867b84d8"
+      "bytes": 230297,
+      "sha256": "437874b1633e73165e3300f55580394663a44759c848288e696859b98f8aad32"
     },
     {
       "id": "single_episode_task_model_radar_json",
@@ -731,7 +731,7 @@
       "shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
       "exists": true,
       "bytes": 50973,
-      "sha256": "d20637e6a17390f7fd44589ff37cb1889318bc39c2259dca6bb7f1a43d8ea26b"
+      "sha256": "38cb43512f2ac40feeb62333bdea89b3a55e5b48468beb8982cf22536f794ecf"
     },
     {
       "id": "episode128_task_model_radar_json",
@@ -741,8 +741,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines and verified Qwen3/Cosmos branches, preserving explicit scoreless cells.",
       "exists": true,
-      "bytes": 187099,
-      "sha256": "bf2b3fdeb9713a9d4cba0e8645c24c325b88e939cb94f4718a9d3c2db03e2bb3"
+      "bytes": 186443,
+      "sha256": "55e758e8703f406889022976d0ba055181212305c9a7246e899463e0c3c3b554"
     },
     {
       "id": "task_method_20_result_matrix_json",
@@ -752,8 +752,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and scoreless cells carry unsupported/not-evaluated reasons.",
       "exists": true,
-      "bytes": 129600,
-      "sha256": "30fd572521991fd7f5741411d91a40d3d442032f001841f9fd1a4e7381eb73d2"
+      "bytes": 129242,
+      "sha256": "64fb700d51f536edf11291799b6173cf9ae8dd7a41178aac348b8207ed4b1e42"
     },
     {
       "id": "task_method_20_result_matrix",
@@ -763,8 +763,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing table that separates 20 records per method from numeric scored axes, documented raw128 proxy scores, unsupported metadata targets, and model targets not evaluated in verified packages.",
       "exists": true,
-      "bytes": 4128,
-      "sha256": "89c73da7db81d2c5f6eb4a16c828531a589ac44cabba2c0c95b171b6ad2060d6"
+      "bytes": 4026,
+      "sha256": "55e949fc30419a52f7f5ec4dd9544a11b253b076f8e3637ec3e92b3d61a89aab"
     },
     {
       "id": "task_method_20_gap_audit_json",
@@ -774,8 +774,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 180-record gap ledger with numeric scores, scoreless cells, explicit status reasons, and next evidence needed before new scores can be published.",
       "exists": true,
-      "bytes": 50687,
-      "sha256": "2cdaa06f9c140a2e194675a3383be341acb1f6e07ddecfa7017cdbe34d704282"
+      "bytes": 46902,
+      "sha256": "2b64dbd013625852679f9b91d25c48d1ed197fec727883b4fe37088b2d594784"
     },
     {
       "id": "task_method_20_gap_audit",
@@ -785,8 +785,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing ledger that lists every scoreless method-task cell and the concrete target or model-output evidence required before it can become numeric.",
       "exists": true,
-      "bytes": 14421,
-      "sha256": "125e658010284dc48570fa7c6a7676e4013d30dd1f22deb24d369e7085a7b700"
+      "bytes": 13387,
+      "sha256": "d33461eb704f8e92545b6b54d9fc509e617fbacc9ca9894ac851ca9c3dec0fec"
     },
     {
       "id": "unified_task_model_radar_chart",
@@ -796,8 +796,8 @@
       "surface": "website_hf",
       "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3/Cosmos task-aligned model overlays.",
       "exists": true,
-      "bytes": 50841,
-      "sha256": "e5fa2420fc5ed905953e71ef8978ad1ee794c0daf06a7f0ff10374db7f291c72"
+      "bytes": 51953,
+      "sha256": "19c001f10319946ef0e4921064f8a012836f29e7c8b272f900c257169faf46a1"
     },
     {
       "id": "single_episode_task_model_radar_chart",
@@ -818,8 +818,8 @@
       "surface": "website_hf",
       "shows": "Separates the selected 128-episode methods: raw-feature simple/NN as complete 20/20 scored polygons and metadata/Qwen/Cosmos as task-aligned overlays.",
       "exists": true,
-      "bytes": 44825,
-      "sha256": "50b5d87fca4aba303a8440f5ef53470ed493e9f1251cb5edeb16bac90038a11b"
+      "bytes": 45937,
+      "sha256": "b504b1b9c5cad0caa8c822d5bb2971c1b708251cf7b9ef587a92db2c12751e97"
     },
     {
       "id": "unified_task_model_radar_builder",
@@ -906,8 +906,8 @@
       "surface": "repo_hf",
       "shows": "Rerun of JSONL metadata/text simple and neural baselines over the selected 128-episode multiscale dataset; supports radar overlays on JSONL-supported task axes.",
       "exists": true,
-      "bytes": 50297,
-      "sha256": "1c1710bcf340ece479e321f19d4cb8302fe369a1103b4584a15853fe73dc226c"
+      "bytes": 109248,
+      "sha256": "5e7f3085be5012eb3dda46f9c7b5b7c0ae22d6a0fbce71d6e99dd317fecc12af"
     },
     {
       "id": "a100_128_raw20_task_baselines",
@@ -1105,7 +1105,7 @@
       "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
       "exists": true,
       "bytes": 8100,
-      "sha256": "6549b0f8da6c3742c72b12b71900db1b89455cd34d5befcdf9d249b4adebbd1a"
+      "sha256": "7800195093b8b81b49c87cdcbcebe601de8141c0c9d8b4490b98f539cb132725"
     },
     {
       "id": "public_surface_qa",
@@ -1310,7 +1310,7 @@
       "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": 983979,
+      "bytes": 994053,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1322,7 +1322,7 @@
       "volatile": true,
       "shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
       "exists": true,
-      "bytes": 20022,
+      "bytes": 20021,
       "hash_policy": "existence_and_size_only"
     },
     {

docs/data/episode128_task_model_radar.json

@@ -1,12 +1,12 @@
 {
   "title": "128-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3/Cosmos branches. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.",
   "task_count": 20,
   "method_count": 7,
   "method_task_record_count": 140,
-  "scored_method_task_count": 83,
+  "scored_method_task_count": 93,
   "normalization_policy": {
     "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
     "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -30,18 +30,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -55,17 +54,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -1295,26 +1294,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.004579592783699693,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.004579592783699693,
+          "raw_text": "0.0046",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.0029821307969142615,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0029821307969142615,
+          "raw_text": "0.0030",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0024280172369056294,
@@ -1386,26 +1385,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.0001206030150753769,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0001206030150753769,
+          "raw_text": "0.0001",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 2.086049543676662e-05,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 2.086049543676662e-05,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0,
@@ -1479,13 +1478,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1568,26 +1567,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.0,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.0,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0,
@@ -1659,26 +1658,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.17656983343047333,
           "metric_key": "micro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17656983343047333,
+          "raw_text": "0.1766",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.17418550827844048,
           "metric_key": "micro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17418550827844048,
+          "raw_text": "0.1742",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.06469493412657774,
@@ -1752,13 +1751,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1843,13 +1842,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "mrr",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1932,26 +1931,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 624.8108520507812,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.016864874132806403,
+          "raw_text": "624.81",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 41.4664421081543,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.25411768748242325,
+          "raw_text": "41.47",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 52.32759475708008,
@@ -3530,17 +3529,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -3548,17 +3547,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -3656,17 +3655,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -3674,17 +3673,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -3782,17 +3781,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -3908,17 +3907,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -3926,17 +3925,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -4034,17 +4033,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -4052,17 +4051,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -4160,17 +4159,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -4286,17 +4285,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -4412,17 +4411,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -4430,17 +4429,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

docs/data/public_surface_qa.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Public Project Surface",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:41:42+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+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": "2026-06-18T11:18:05+00:00"
+          "generated_at_utc": "2026-06-18T11:41:43+00:00"
         },
         "rendered_site_check": {
           "exists": true,
@@ -43,12 +43,12 @@
         "publication_package": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-18T11:18:57+00:00"
+          "generated_at_utc": "2026-06-18T11:42:48+00:00"
         },
         "mirror_parity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-18T11:21:54+00:00"
+          "generated_at_utc": "2026-06-18T11:43:59+00:00"
         }
       },
       "failures": {}

docs/data/publication_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:42:48+00:00",
+  "generated_at_utc": "2026-06-18T12:10:47+00:00",
   "checks": [
     {
       "name": "required_publication_assets_present",
@@ -215,8 +215,8 @@
     "github_repo": {
       "root": "repo",
       "exists": true,
-      "file_count": 1276,
-      "text_file_count": 1072,
+      "file_count": 1321,
+      "text_file_count": 1108,
       "largest_file": {
         "path": "results/episode_task_suite/modality_reconstruction/predictions.npz",
         "bytes": 55702978
@@ -226,8 +226,8 @@
     "hf_space_bundle": {
       "root": "hf_publish/space",
       "exists": true,
-      "file_count": 1058,
-      "text_file_count": 879,
+      "file_count": 1103,
+      "text_file_count": 915,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061
@@ -237,8 +237,8 @@
     "hf_artifact_bundle": {
       "root": "hf_publish/artifacts",
       "exists": true,
-      "file_count": 2537,
-      "text_file_count": 1085,
+      "file_count": 2582,
+      "text_file_count": 1121,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061
@@ -248,8 +248,8 @@
     "hf_model_bundle": {
       "root": "hf_publish/model",
       "exists": true,
-      "file_count": 2956,
-      "text_file_count": 1247,
+      "file_count": 3001,
+      "text_file_count": 1283,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061

docs/data/quality_gates.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Release Checks",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:20:56+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+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": "2026-06-18T11:18:06+00:00",
+  "generated_at_utc": "2026-06-18T12:09:48+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": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "description": "Minimal and Neural MLP baselines on the one public sample episode, both scored on all 20 task contracts.",
   "task_count": 20,
   "method_count": 2,

docs/data/source_alignment_audit.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Source Alignment Note",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:18:04+00:00",
+  "generated_at_utc": "2026-06-18T12:09:45+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_gap_audit.json

@@ -1,10 +1,10 @@
 {
-  "generated_at_utc": "2026-06-18T11:15:34+00:00",
+  "generated_at_utc": "2026-06-18T12:07:14+00:00",
   "immediate_actions": [
     {
       "artifact": "docs/data/task_method_20_gap_audit.json",
       "id": "gap_audit",
-      "purpose": "Keep the 57 scoreless cells visible and reproducible."
+      "purpose": "Keep the 53 scoreless cells visible and reproducible."
     },
     {
       "artifact": "scripts/omni/score_model_output_probes.py",
@@ -50,11 +50,12 @@
       "proxy_scored_task_count": 0,
       "result_record_count": 20,
       "scope": "128 selected episodes, JSONL metadata/text only",
-      "scored_task_count": 8,
-      "scoreless_task_count": 12,
+      "scored_task_count": 7,
+      "scoreless_task_count": 13,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 7,
+        "unsupported_without_required_target": 6
       }
     },
     "metadata128_simple": {
@@ -63,12 +64,11 @@
       "proxy_scored_task_count": 0,
       "result_record_count": 20,
       "scope": "128 selected episodes, JSONL metadata/text only",
-      "scored_task_count": 8,
-      "scoreless_task_count": 12,
+      "scored_task_count": 13,
+      "scoreless_task_count": 7,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       }
     },
     "minimal": {
@@ -138,18 +138,25 @@
   "missing_by_method": {
     "cosmos3_nano_future_window": 15,
     "cosmos3_super_reasoner": 13,
-    "metadata128_neural_mlp": 12,
-    "metadata128_simple": 12,
+    "metadata128_neural_mlp": 13,
+    "metadata128_simple": 7,
     "qwen3_omni_v6_lora": 5
   },
   "missing_by_status": {
     "not_evaluated_in_verified_package": 33,
-    "not_supported_by_metadata_only_package": 20,
-    "unsupported_without_required_target": 4
+    "not_supported_by_metadata_only_package": 7,
+    "unsupported_without_required_target": 13
   },
   "missing_by_task": {
+    "01 Action Recognition": [
+      "metadata128_neural_mlp"
+    ],
     "02 Procedure Step Recognition": [
-      "cosmos3_nano_future_window"
+      "cosmos3_nano_future_window",
+      "metadata128_neural_mlp"
+    ],
+    "04 Next-Action Prediction": [
+      "metadata128_neural_mlp"
     ],
     "05 Hand Trajectory Forecasting": [
       "cosmos3_nano_future_window",
@@ -190,14 +197,12 @@
     "13 Long-Horizon Next-Action Forecasting": [
       "cosmos3_nano_future_window",
       "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "14 Long-Horizon Next-Subtask Forecasting": [
       "cosmos3_nano_future_window",
       "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "15 Interaction Text Prediction": [
       "cosmos3_nano_future_window",
@@ -208,14 +213,11 @@
     ],
     "16 Action-Object Relation Prediction": [
       "cosmos3_nano_future_window",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "17 Future Object-Set Forecasting": [
       "cosmos3_nano_future_window",
-      "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "cosmos3_super_reasoner"
     ],
     "18 IMU-to-Hand Pose Reconstruction": [
       "cosmos3_nano_future_window",
@@ -233,12 +235,36 @@
     ],
     "20 Time-to-Next-Transition Regression": [
       "cosmos3_nano_future_window",
-      "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "cosmos3_super_reasoner"
     ]
   },
   "missing_records": [
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 896 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "timeline_action",
+      "task_label": "Action Recognition",
+      "task_number": 1
+    },
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 652 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "timeline_subtask",
+      "task_label": "Procedure Step Recognition",
+      "task_number": 2
+    },
     {
       "method": "Cosmos3-Nano Future Window",
       "metric_key": "macro_f1",
@@ -252,6 +278,19 @@
       "task_label": "Procedure Step Recognition",
       "task_number": 2
     },
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 891 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "next_action",
+      "task_label": "Next-Action Prediction",
+      "task_number": 4
+    },
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mpjpe",
@@ -538,28 +577,15 @@
       "task_label": "Multimodal Synchronization Detection",
       "task_number": 12
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "long_horizon_next_action",
-      "task_label": "Long-Horizon Next-Action Forecasting",
-      "task_number": 13
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 887 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "long_horizon_next_action",
       "task_label": "Long-Horizon Next-Action Forecasting",
       "task_number": 13
@@ -590,28 +616,15 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "task_number": 13
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "next_subtask_forecast",
-      "task_label": "Long-Horizon Next-Subtask Forecasting",
-      "task_number": 14
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 651 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "next_subtask_forecast",
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "task_number": 14
@@ -645,12 +658,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "interaction_text_prediction",
       "task_label": "Interaction Text Prediction",
       "task_number": 15
@@ -707,28 +720,15 @@
       "task_label": "Interaction Text Prediction",
       "task_number": 15
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "action_object_relation",
-      "task_label": "Action-Object Relation Prediction",
-      "task_number": 16
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 3058 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "action_object_relation",
       "task_label": "Action-Object Relation Prediction",
       "task_number": 16
@@ -746,32 +746,6 @@
       "task_label": "Action-Object Relation Prediction",
       "task_number": 16
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "micro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "object_set_forecast",
-      "task_label": "Future Object-Set Forecasting",
-      "task_number": 17
-    },
-    {
-      "method": "128ep Metadata NN",
-      "metric_key": "micro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "object_set_forecast",
-      "task_label": "Future Object-Set Forecasting",
-      "task_number": 17
-    },
     {
       "method": "Cosmos3-Super Reasoner",
       "metric_key": "micro_f1",
@@ -801,12 +775,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "imu_to_hand_pose",
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "task_number": 18
@@ -866,12 +840,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mrr",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "camera_view_sync_retrieval",
       "task_label": "Camera-View Synchronization Retrieval",
       "task_number": 19
@@ -928,32 +902,6 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "task_number": 19
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "time_to_transition",
-      "task_label": "Time-to-Next-Transition Regression",
-      "task_number": 20
-    },
-    {
-      "method": "128ep Metadata NN",
-      "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "time_to_transition",
-      "task_label": "Time-to-Next-Transition Regression",
-      "task_number": 20
-    },
     {
       "method": "Cosmos3-Super Reasoner",
       "metric_key": "mae",
@@ -1027,8 +975,8 @@
     "method_count": 9,
     "method_task_record_count": 180,
     "proxy_scored_method_task_count": 4,
-    "scored_method_task_count": 123,
-    "scoreless_method_task_count": 57,
+    "scored_method_task_count": 127,
+    "scoreless_method_task_count": 53,
     "task_count": 20
   },
   "source_matrix": "docs/data/task_method_20_result_matrix.json",

docs/data/task_method_20_result_matrix.json

@@ -1,11 +1,11 @@
 {
   "title": "Task Method 20-Result Matrix",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
-  "scored_method_task_count": 123,
+  "scored_method_task_count": 133,
   "series": [
     {
       "id": "minimal",
@@ -64,18 +64,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -89,17 +88,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -2210,17 +2209,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -2228,17 +2227,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -2372,17 +2371,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -2390,17 +2389,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -2534,17 +2533,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -2696,17 +2695,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -2714,17 +2713,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -2858,17 +2857,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -2876,17 +2875,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -3020,17 +3019,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -3182,17 +3181,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -3344,17 +3343,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -3362,17 +3361,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

docs/data/task_surface_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:18:04+00:00",
+  "generated_at_utc": "2026-06-18T12:09:25+00:00",
   "summary": {
     "task_count": 12,
     "expected_task_count": 12,

docs/data/unified_task_model_radar.json

@@ -1,11 +1,11 @@
 {
   "title": "Unified 20-Task Model Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
-  "scored_method_task_count": 123,
+  "scored_method_task_count": 133,
   "normalization_policy": {
     "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
     "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -73,18 +73,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -98,17 +97,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -1608,6 +1607,28 @@
           "raw_text": "0.0023",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.004579592783699693,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.004579592783699693,
+          "raw_text": "0.0046",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.0029821307969142615,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0029821307969142615,
+          "raw_text": "0.0030",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0024280172369056294,
           "metric_key": "macro_f1",
@@ -1630,28 +1651,6 @@
           "raw_text": "0.0011",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1719,6 +1718,28 @@
           "raw_text": "0.0042",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.0001206030150753769,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0001206030150753769,
+          "raw_text": "0.0001",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 2.086049543676662e-05,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 2.086049543676662e-05,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0,
           "metric_key": "macro_f1",
@@ -1741,28 +1762,6 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1819,6 +1818,17 @@
           "raw_text": "0.0381",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.012611998261547169,
           "metric_key": "macro_f1",
@@ -1841,17 +1851,6 @@
           "raw_text": "0.0098",
           "status_label": "proxy scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1952,6 +1951,28 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.0,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.0,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0,
           "metric_key": "macro_f1",
@@ -1974,28 +1995,6 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_nano_future_window": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -2052,6 +2051,28 @@
           "raw_text": "0.1659",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.17656983343047333,
+          "metric_key": "micro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17656983343047333,
+          "raw_text": "0.1766",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.17418550827844048,
+          "metric_key": "micro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17418550827844048,
+          "raw_text": "0.1742",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.06469493412657774,
           "metric_key": "micro_f1",
@@ -2074,28 +2095,6 @@
           "raw_text": "0.1752",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "micro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "micro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "micro_f1",
@@ -2152,6 +2151,17 @@
           "raw_text": "0.0426",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.22941437363624573,
           "metric_key": "mae",
@@ -2174,17 +2184,6 @@
           "raw_text": "0.2530",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "mae",
@@ -2263,6 +2262,17 @@
           "raw_text": "0.2409",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "mrr",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.0026625150348991156,
           "metric_key": "mrr",
@@ -2285,17 +2295,6 @@
           "raw_text": "0.0025",
           "status_label": "proxy scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mrr",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "mrr",
@@ -2385,6 +2384,28 @@
           "raw_text": "134.07",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 624.8108520507812,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.016864874132806403,
+          "raw_text": "624.81",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 41.4664421081543,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.25411768748242325,
+          "raw_text": "41.47",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 52.32759475708008,
           "metric_key": "mae",
@@ -2407,28 +2428,6 @@
           "raw_text": "42.37",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "mae",
@@ -2459,7 +2458,7 @@
       "id": "metadata128_simple",
       "title": "128ep Metadata Simple",
       "status": "a100_rerun_pass",
-      "coverage": "20 records / 8 scored JSONL-supported axes",
+      "coverage": "20 records / 13 scored JSONL-supported axes",
       "headline": "34,269 rows; train/val/test 25,629/4,608/4,032",
       "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/summary_report.json"
     },
@@ -2467,7 +2466,7 @@
       "id": "metadata128_neural_mlp",
       "title": "128ep Metadata NN",
       "status": "a100_rerun_pass",
-      "coverage": "20 records / 8 scored JSONL-supported axes",
+      "coverage": "20 records / 13 scored JSONL-supported axes",
       "headline": "compact MLP heads over metadata/text features",
       "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/summary_report.json"
     },
@@ -4508,17 +4507,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -4526,17 +4525,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -4670,17 +4669,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -4688,17 +4687,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -4832,17 +4831,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -4994,17 +4993,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -5012,17 +5011,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -5156,17 +5155,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -5174,17 +5173,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -5318,17 +5317,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -5480,17 +5479,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -5642,17 +5641,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -5660,17 +5659,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

docs/data/website_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:41:43+00:00",
+  "generated_at_utc": "2026-06-18T12:09:46+00:00",
   "docs_root": "docs",
   "site_base": "/ropedia-xperience-10m-task-suite/",
   "summary": {
@@ -301,7 +301,7 @@
     },
     {
       "path": "data/artifact_index.json",
-      "bytes": 116109,
+      "bytes": 116110,
       "top_level_type": "dict"
     },
     {
@@ -316,7 +316,7 @@
     },
     {
       "path": "data/episode128_task_model_radar.json",
-      "bytes": 187099,
+      "bytes": 186443,
       "top_level_type": "dict"
     },
     {
@@ -486,12 +486,12 @@
     },
     {
       "path": "data/task_method_20_gap_audit.json",
-      "bytes": 50687,
+      "bytes": 46902,
       "top_level_type": "dict"
     },
     {
       "path": "data/task_method_20_result_matrix.json",
-      "bytes": 129600,
+      "bytes": 129242,
       "top_level_type": "dict"
     },
     {
@@ -526,7 +526,7 @@
     },
     {
       "path": "data/unified_task_model_radar.json",
-      "bytes": 230951,
+      "bytes": 230297,
       "top_level_type": "dict"
     },
     {
@@ -571,7 +571,7 @@
     {
       "path": "assets/charts/episode128_task_model_radar.svg",
       "exists": true,
-      "bytes": 44825,
+      "bytes": 45937,
       "format": "SVG",
       "has_viewbox": true
     },
@@ -641,7 +641,7 @@
     {
       "path": "assets/charts/unified_task_model_radar.svg",
       "exists": true,
-      "bytes": 50841,
+      "bytes": 51953,
       "format": "SVG",
       "has_viewbox": true
     },

metrics/artifact_index.json

@@ -1,6 +1,6 @@
 {
   "title": "Ropedia Xperience-10M Task Suite Artifact Index",
-  "generated_at_utc": "2026-06-18T11:16:44+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+00:00",
   "status": "pass",
   "artifact_count": 213,
   "missing": [],
@@ -290,8 +290,8 @@
       "surface": "repo_hf",
       "shows": "Runs simple metadata and neural MLP baselines on the same selected 96/16/16 episode split used by the Qwen3-Omni diagnostic pilot.",
       "exists": true,
-      "bytes": 58012,
-      "sha256": "a95cdde097b11f83023c758c807f031c3d4cb3fde20d42ed314565440cc68374"
+      "bytes": 73236,
+      "sha256": "76acae0de25d51413e7e6f11021163e7d9909cfe95d65bf6b02e74043d429e2d"
     },
     {
       "id": "task_suite_enhancement_128",
@@ -599,7 +599,7 @@
       "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
       "exists": true,
       "bytes": 4432,
-      "sha256": "8494b6983100acdfde9b5929e871b27120897af8ec7b5a3031aa142b598a09ae"
+      "sha256": "ae089cc0df132b63365e03b2157a488b5d1569567c0374d7621bcd347da62c9e"
     },
     {
       "id": "source_alignment_validator",
@@ -719,8 +719,8 @@
       "surface": "website_hf",
       "shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3/Cosmos overlay mappings, branch-card caveats, and explicit scoreless status records.",
       "exists": true,
-      "bytes": 230951,
-      "sha256": "8aaed21d08943f2dc53c5160e27872bc4f7f8a405d7289cdaaf7b00d867b84d8"
+      "bytes": 230297,
+      "sha256": "437874b1633e73165e3300f55580394663a44759c848288e696859b98f8aad32"
     },
     {
       "id": "single_episode_task_model_radar_json",
@@ -731,7 +731,7 @@
       "shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
       "exists": true,
       "bytes": 50973,
-      "sha256": "d20637e6a17390f7fd44589ff37cb1889318bc39c2259dca6bb7f1a43d8ea26b"
+      "sha256": "38cb43512f2ac40feeb62333bdea89b3a55e5b48468beb8982cf22536f794ecf"
     },
     {
       "id": "episode128_task_model_radar_json",
@@ -741,8 +741,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines and verified Qwen3/Cosmos branches, preserving explicit scoreless cells.",
       "exists": true,
-      "bytes": 187099,
-      "sha256": "bf2b3fdeb9713a9d4cba0e8645c24c325b88e939cb94f4718a9d3c2db03e2bb3"
+      "bytes": 186443,
+      "sha256": "55e758e8703f406889022976d0ba055181212305c9a7246e899463e0c3c3b554"
     },
     {
       "id": "task_method_20_result_matrix_json",
@@ -752,8 +752,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and scoreless cells carry unsupported/not-evaluated reasons.",
       "exists": true,
-      "bytes": 129600,
-      "sha256": "30fd572521991fd7f5741411d91a40d3d442032f001841f9fd1a4e7381eb73d2"
+      "bytes": 129242,
+      "sha256": "64fb700d51f536edf11291799b6173cf9ae8dd7a41178aac348b8207ed4b1e42"
     },
     {
       "id": "task_method_20_result_matrix",
@@ -763,8 +763,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing table that separates 20 records per method from numeric scored axes, documented raw128 proxy scores, unsupported metadata targets, and model targets not evaluated in verified packages.",
       "exists": true,
-      "bytes": 4128,
-      "sha256": "89c73da7db81d2c5f6eb4a16c828531a589ac44cabba2c0c95b171b6ad2060d6"
+      "bytes": 4026,
+      "sha256": "55e949fc30419a52f7f5ec4dd9544a11b253b076f8e3637ec3e92b3d61a89aab"
     },
     {
       "id": "task_method_20_gap_audit_json",
@@ -774,8 +774,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable 180-record gap ledger with numeric scores, scoreless cells, explicit status reasons, and next evidence needed before new scores can be published.",
       "exists": true,
-      "bytes": 50687,
-      "sha256": "2cdaa06f9c140a2e194675a3383be341acb1f6e07ddecfa7017cdbe34d704282"
+      "bytes": 46902,
+      "sha256": "2b64dbd013625852679f9b91d25c48d1ed197fec727883b4fe37088b2d594784"
     },
     {
       "id": "task_method_20_gap_audit",
@@ -785,8 +785,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing ledger that lists every scoreless method-task cell and the concrete target or model-output evidence required before it can become numeric.",
       "exists": true,
-      "bytes": 14421,
-      "sha256": "125e658010284dc48570fa7c6a7676e4013d30dd1f22deb24d369e7085a7b700"
+      "bytes": 13387,
+      "sha256": "d33461eb704f8e92545b6b54d9fc509e617fbacc9ca9894ac851ca9c3dec0fec"
     },
     {
       "id": "unified_task_model_radar_chart",
@@ -796,8 +796,8 @@
       "surface": "website_hf",
       "shows": "Compares minimal and neural MLP baselines across all 20 tasks, with Qwen3/Cosmos task-aligned model overlays.",
       "exists": true,
-      "bytes": 50841,
-      "sha256": "e5fa2420fc5ed905953e71ef8978ad1ee794c0daf06a7f0ff10374db7f291c72"
+      "bytes": 51953,
+      "sha256": "19c001f10319946ef0e4921064f8a012836f29e7c8b272f900c257169faf46a1"
     },
     {
       "id": "single_episode_task_model_radar_chart",
@@ -818,8 +818,8 @@
       "surface": "website_hf",
       "shows": "Separates the selected 128-episode methods: raw-feature simple/NN as complete 20/20 scored polygons and metadata/Qwen/Cosmos as task-aligned overlays.",
       "exists": true,
-      "bytes": 44825,
-      "sha256": "50b5d87fca4aba303a8440f5ef53470ed493e9f1251cb5edeb16bac90038a11b"
+      "bytes": 45937,
+      "sha256": "b504b1b9c5cad0caa8c822d5bb2971c1b708251cf7b9ef587a92db2c12751e97"
     },
     {
       "id": "unified_task_model_radar_builder",
@@ -906,8 +906,8 @@
       "surface": "repo_hf",
       "shows": "Rerun of JSONL metadata/text simple and neural baselines over the selected 128-episode multiscale dataset; supports radar overlays on JSONL-supported task axes.",
       "exists": true,
-      "bytes": 50297,
-      "sha256": "1c1710bcf340ece479e321f19d4cb8302fe369a1103b4584a15853fe73dc226c"
+      "bytes": 109248,
+      "sha256": "5e7f3085be5012eb3dda46f9c7b5b7c0ae22d6a0fbce71d6e99dd317fecc12af"
     },
     {
       "id": "a100_128_raw20_task_baselines",
@@ -1105,7 +1105,7 @@
       "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
       "exists": true,
       "bytes": 8100,
-      "sha256": "6549b0f8da6c3742c72b12b71900db1b89455cd34d5befcdf9d249b4adebbd1a"
+      "sha256": "7800195093b8b81b49c87cdcbcebe601de8141c0c9d8b4490b98f539cb132725"
     },
     {
       "id": "public_surface_qa",
@@ -1310,7 +1310,7 @@
       "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": 983979,
+      "bytes": 994053,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -1322,7 +1322,7 @@
       "volatile": true,
       "shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
       "exists": true,
-      "bytes": 20022,
+      "bytes": 20021,
       "hash_policy": "existence_and_size_only"
     },
     {

metrics/episode128_task_model_radar.json

@@ -1,12 +1,12 @@
 {
   "title": "128-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3/Cosmos branches. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.",
   "task_count": 20,
   "method_count": 7,
   "method_task_record_count": 140,
-  "scored_method_task_count": 83,
+  "scored_method_task_count": 93,
   "normalization_policy": {
     "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
     "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -30,18 +30,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -55,17 +54,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -1295,26 +1294,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.004579592783699693,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.004579592783699693,
+          "raw_text": "0.0046",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.0029821307969142615,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0029821307969142615,
+          "raw_text": "0.0030",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0024280172369056294,
@@ -1386,26 +1385,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.0001206030150753769,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0001206030150753769,
+          "raw_text": "0.0001",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 2.086049543676662e-05,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 2.086049543676662e-05,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0,
@@ -1479,13 +1478,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1568,26 +1567,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.0,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.0,
           "metric_key": "macro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.0,
@@ -1659,26 +1658,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 0.17656983343047333,
           "metric_key": "micro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17656983343047333,
+          "raw_text": "0.1766",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 0.17418550827844048,
           "metric_key": "micro_f1",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17418550827844048,
+          "raw_text": "0.1742",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 0.06469493412657774,
@@ -1752,13 +1751,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1843,13 +1842,13 @@
         "metadata128_simple": {
           "raw": null,
           "metric_key": "mrr",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
+          "status": "unsupported_without_required_target",
+          "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
           "normalized_score": null,
           "raw_text": "n/a",
-          "status_label": "not supported"
+          "status_label": "unsupported"
         },
         "metadata128_neural_mlp": {
           "raw": null,
@@ -1932,26 +1931,26 @@
       "raw128_proxy_axis": false,
       "values": {
         "metadata128_simple": {
-          "raw": null,
+          "raw": 624.8108520507812,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.016864874132806403,
+          "raw_text": "624.81",
+          "status_label": "scored"
         },
         "metadata128_neural_mlp": {
-          "raw": null,
+          "raw": 41.4664421081543,
           "metric_key": "mae",
-          "source": null,
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
           "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.25411768748242325,
+          "raw_text": "41.47",
+          "status_label": "scored"
         },
         "raw128_simple": {
           "raw": 52.32759475708008,
@@ -3530,17 +3529,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -3548,17 +3547,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -3656,17 +3655,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -3674,17 +3673,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -3782,17 +3781,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -3908,17 +3907,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -3926,17 +3925,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -4034,17 +4033,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -4052,17 +4051,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -4160,17 +4159,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -4286,17 +4285,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -4412,17 +4411,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -4430,17 +4429,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

metrics/public_surface_qa.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Public Project Surface",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:41:42+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+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": "2026-06-18T11:18:05+00:00"
+          "generated_at_utc": "2026-06-18T11:41:43+00:00"
         },
         "rendered_site_check": {
           "exists": true,
@@ -43,12 +43,12 @@
         "publication_package": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-18T11:18:57+00:00"
+          "generated_at_utc": "2026-06-18T11:42:48+00:00"
         },
         "mirror_parity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-18T11:21:54+00:00"
+          "generated_at_utc": "2026-06-18T11:43:59+00:00"
         }
       },
       "failures": {}

metrics/publication_audit.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:42:48+00:00",
+  "generated_at_utc": "2026-06-18T12:10:47+00:00",
   "checks": [
     {
       "name": "required_publication_assets_present",
@@ -215,8 +215,8 @@
     "github_repo": {
       "root": "repo",
       "exists": true,
-      "file_count": 1276,
-      "text_file_count": 1072,
+      "file_count": 1321,
+      "text_file_count": 1108,
       "largest_file": {
         "path": "results/episode_task_suite/modality_reconstruction/predictions.npz",
         "bytes": 55702978
@@ -226,8 +226,8 @@
     "hf_space_bundle": {
       "root": "hf_publish/space",
       "exists": true,
-      "file_count": 1058,
-      "text_file_count": 879,
+      "file_count": 1103,
+      "text_file_count": 915,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061
@@ -237,8 +237,8 @@
     "hf_artifact_bundle": {
       "root": "hf_publish/artifacts",
       "exists": true,
-      "file_count": 2537,
-      "text_file_count": 1085,
+      "file_count": 2582,
+      "text_file_count": 1121,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061
@@ -248,8 +248,8 @@
     "hf_model_bundle": {
       "root": "hf_publish/model",
       "exists": true,
-      "file_count": 2956,
-      "text_file_count": 1247,
+      "file_count": 3001,
+      "text_file_count": 1283,
       "largest_file": {
         "path": "results/omni_finetune/xperience10m_128ep_dense_multiscale_hierarchical_v1_20260608/dense_multiscale_windows.jsonl",
         "bytes": 135591061

metrics/quality_gates.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Release Checks",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:20:56+00:00",
+  "generated_at_utc": "2026-06-18T12:09:24+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": "2026-06-18T11:18:06+00:00",
+  "generated_at_utc": "2026-06-18T12:09:48+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": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+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,

metrics/source_alignment_audit.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Source Alignment Note",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:18:04+00:00",
+  "generated_at_utc": "2026-06-18T12:09:45+00:00",
   "alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
   "alignment_summary": {
     "full_dataset_repo": "ropedia-ai/xperience-10m",

metrics/task_method_20_gap_audit.json

@@ -1,10 +1,10 @@
 {
-  "generated_at_utc": "2026-06-18T11:15:34+00:00",
+  "generated_at_utc": "2026-06-18T12:07:14+00:00",
   "immediate_actions": [
     {
       "artifact": "docs/data/task_method_20_gap_audit.json",
       "id": "gap_audit",
-      "purpose": "Keep the 57 scoreless cells visible and reproducible."
+      "purpose": "Keep the 53 scoreless cells visible and reproducible."
     },
     {
       "artifact": "scripts/omni/score_model_output_probes.py",
@@ -50,11 +50,12 @@
       "proxy_scored_task_count": 0,
       "result_record_count": 20,
       "scope": "128 selected episodes, JSONL metadata/text only",
-      "scored_task_count": 8,
-      "scoreless_task_count": 12,
+      "scored_task_count": 7,
+      "scoreless_task_count": 13,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 7,
+        "unsupported_without_required_target": 6
       }
     },
     "metadata128_simple": {
@@ -63,12 +64,11 @@
       "proxy_scored_task_count": 0,
       "result_record_count": 20,
       "scope": "128 selected episodes, JSONL metadata/text only",
-      "scored_task_count": 8,
-      "scoreless_task_count": 12,
+      "scored_task_count": 13,
+      "scoreless_task_count": 7,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       }
     },
     "minimal": {
@@ -138,18 +138,25 @@
   "missing_by_method": {
     "cosmos3_nano_future_window": 15,
     "cosmos3_super_reasoner": 13,
-    "metadata128_neural_mlp": 12,
-    "metadata128_simple": 12,
+    "metadata128_neural_mlp": 13,
+    "metadata128_simple": 7,
     "qwen3_omni_v6_lora": 5
   },
   "missing_by_status": {
     "not_evaluated_in_verified_package": 33,
-    "not_supported_by_metadata_only_package": 20,
-    "unsupported_without_required_target": 4
+    "not_supported_by_metadata_only_package": 7,
+    "unsupported_without_required_target": 13
   },
   "missing_by_task": {
+    "01 Action Recognition": [
+      "metadata128_neural_mlp"
+    ],
     "02 Procedure Step Recognition": [
-      "cosmos3_nano_future_window"
+      "cosmos3_nano_future_window",
+      "metadata128_neural_mlp"
+    ],
+    "04 Next-Action Prediction": [
+      "metadata128_neural_mlp"
     ],
     "05 Hand Trajectory Forecasting": [
       "cosmos3_nano_future_window",
@@ -190,14 +197,12 @@
     "13 Long-Horizon Next-Action Forecasting": [
       "cosmos3_nano_future_window",
       "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "14 Long-Horizon Next-Subtask Forecasting": [
       "cosmos3_nano_future_window",
       "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "15 Interaction Text Prediction": [
       "cosmos3_nano_future_window",
@@ -208,14 +213,11 @@
     ],
     "16 Action-Object Relation Prediction": [
       "cosmos3_nano_future_window",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "metadata128_neural_mlp"
     ],
     "17 Future Object-Set Forecasting": [
       "cosmos3_nano_future_window",
-      "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "cosmos3_super_reasoner"
     ],
     "18 IMU-to-Hand Pose Reconstruction": [
       "cosmos3_nano_future_window",
@@ -233,12 +235,36 @@
     ],
     "20 Time-to-Next-Transition Regression": [
       "cosmos3_nano_future_window",
-      "cosmos3_super_reasoner",
-      "metadata128_neural_mlp",
-      "metadata128_simple"
+      "cosmos3_super_reasoner"
     ]
   },
   "missing_records": [
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 896 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "timeline_action",
+      "task_label": "Action Recognition",
+      "task_number": 1
+    },
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 652 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "timeline_subtask",
+      "task_label": "Procedure Step Recognition",
+      "task_number": 2
+    },
     {
       "method": "Cosmos3-Nano Future Window",
       "metric_key": "macro_f1",
@@ -252,6 +278,19 @@
       "task_label": "Procedure Step Recognition",
       "task_number": 2
     },
+    {
+      "method": "128ep Metadata NN",
+      "metric_key": "macro_f1",
+      "reason": "train class count 891 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
+      "scope": "multi_episode_128_metadata_baseline",
+      "series_id": "metadata128_neural_mlp",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
+      "task_id": "next_action",
+      "task_label": "Next-Action Prediction",
+      "task_number": 4
+    },
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mpjpe",
@@ -538,28 +577,15 @@
       "task_label": "Multimodal Synchronization Detection",
       "task_number": 12
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "long_horizon_next_action",
-      "task_label": "Long-Horizon Next-Action Forecasting",
-      "task_number": 13
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 887 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "long_horizon_next_action",
       "task_label": "Long-Horizon Next-Action Forecasting",
       "task_number": 13
@@ -590,28 +616,15 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "task_number": 13
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "next_subtask_forecast",
-      "task_label": "Long-Horizon Next-Subtask Forecasting",
-      "task_number": 14
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 651 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "next_subtask_forecast",
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "task_number": 14
@@ -645,12 +658,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "interaction_text_prediction",
       "task_label": "Interaction Text Prediction",
       "task_number": 15
@@ -707,28 +720,15 @@
       "task_label": "Interaction Text Prediction",
       "task_number": 15
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "action_object_relation",
-      "task_label": "Action-Object Relation Prediction",
-      "task_number": 16
-    },
     {
       "method": "128ep Metadata NN",
       "metric_key": "macro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "train class count 3058 exceeds --max-neural-classes 512",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "action_object_relation",
       "task_label": "Action-Object Relation Prediction",
       "task_number": 16
@@ -746,32 +746,6 @@
       "task_label": "Action-Object Relation Prediction",
       "task_number": 16
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "micro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "object_set_forecast",
-      "task_label": "Future Object-Set Forecasting",
-      "task_number": 17
-    },
-    {
-      "method": "128ep Metadata NN",
-      "metric_key": "micro_f1",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "object_set_forecast",
-      "task_label": "Future Object-Set Forecasting",
-      "task_number": 17
-    },
     {
       "method": "Cosmos3-Super Reasoner",
       "metric_key": "micro_f1",
@@ -801,12 +775,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "imu_to_hand_pose",
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "task_number": 18
@@ -866,12 +840,12 @@
     {
       "method": "128ep Metadata Simple",
       "metric_key": "mrr",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
+      "recommended_next_step": "Export the missing target field for this 128-episode method, then rerun the same train/validation/test split.",
       "scope": "multi_episode_128_metadata_baseline",
       "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "task_id": "camera_view_sync_retrieval",
       "task_label": "Camera-View Synchronization Retrieval",
       "task_number": 19
@@ -928,32 +902,6 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "task_number": 19
     },
-    {
-      "method": "128ep Metadata Simple",
-      "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "time_to_transition",
-      "task_label": "Time-to-Next-Transition Regression",
-      "task_number": 20
-    },
-    {
-      "method": "128ep Metadata NN",
-      "metric_key": "mae",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-      "recommended_next_step": "Run the task with raw sensor-feature blocks or add a task-specific metadata target builder before assigning a numeric score.",
-      "scope": "multi_episode_128_metadata_baseline",
-      "series_id": "metadata128_neural_mlp",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "task_id": "time_to_transition",
-      "task_label": "Time-to-Next-Transition Regression",
-      "task_number": 20
-    },
     {
       "method": "Cosmos3-Super Reasoner",
       "metric_key": "mae",
@@ -1027,8 +975,8 @@
     "method_count": 9,
     "method_task_record_count": 180,
     "proxy_scored_method_task_count": 4,
-    "scored_method_task_count": 123,
-    "scoreless_method_task_count": 57,
+    "scored_method_task_count": 127,
+    "scoreless_method_task_count": 53,
     "task_count": 20
   },
   "source_matrix": "docs/data/task_method_20_result_matrix.json",

metrics/task_method_20_result_matrix.json

@@ -1,11 +1,11 @@
 {
   "title": "Task Method 20-Result Matrix",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
-  "scored_method_task_count": 123,
+  "scored_method_task_count": 133,
   "series": [
     {
       "id": "minimal",
@@ -64,18 +64,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -89,17 +88,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -2210,17 +2209,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -2228,17 +2227,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -2372,17 +2371,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -2390,17 +2389,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -2534,17 +2533,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -2696,17 +2695,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -2714,17 +2713,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -2858,17 +2857,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -2876,17 +2875,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -3020,17 +3019,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -3182,17 +3181,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -3344,17 +3343,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -3362,17 +3361,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

metrics/task_surface_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:18:04+00:00",
+  "generated_at_utc": "2026-06-18T12:09:25+00:00",
   "summary": {
     "task_count": 12,
     "expected_task_count": 12,

metrics/unified_task_model_radar.json

@@ -1,11 +1,11 @@
 {
   "title": "Unified 20-Task Model Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:15:02+00:00",
+  "generated_at_utc": "2026-06-18T12:07:15+00:00",
   "task_count": 20,
   "method_count": 9,
   "method_task_record_count": 180,
-  "scored_method_task_count": 123,
+  "scored_method_task_count": 133,
   "normalization_policy": {
     "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
     "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
@@ -73,18 +73,17 @@
       "method_detail": "128-episode JSONL metadata/text simple baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 8,
-        "scored": 8,
-        "unsupported_without_required_target": 4
+        "scored": 13,
+        "unsupported_without_required_target": 7
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -98,17 +97,17 @@
       "method_detail": "128-episode JSONL metadata/text MLP baselines.",
       "plotted_as": "colored point overlay",
       "result_record_count": 20,
-      "scored_task_count": 8,
-      "covered_task_count": 8,
+      "scored_task_count": 13,
+      "covered_task_count": 13,
       "proxy_scored_task_count": 0,
-      "scoreless_task_count": 12,
-      "unsupported_task_count": 12,
+      "scoreless_task_count": 7,
+      "unsupported_task_count": 7,
       "not_evaluated_task_count": 0,
       "status_counts": {
-        "not_supported_by_metadata_only_package": 12,
-        "scored": 8
+        "not_supported_by_metadata_only_package": 7,
+        "scored": 13
       },
-      "coverage_fraction": 0.4,
+      "coverage_fraction": 0.65,
       "result_record_fraction": 1.0
     },
     {
@@ -1608,6 +1607,28 @@
           "raw_text": "0.0023",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.004579592783699693,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.004579592783699693,
+          "raw_text": "0.0046",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.0029821307969142615,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0029821307969142615,
+          "raw_text": "0.0030",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0024280172369056294,
           "metric_key": "macro_f1",
@@ -1630,28 +1651,6 @@
           "raw_text": "0.0011",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1719,6 +1718,28 @@
           "raw_text": "0.0042",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.0001206030150753769,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0001206030150753769,
+          "raw_text": "0.0001",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 2.086049543676662e-05,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 2.086049543676662e-05,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0,
           "metric_key": "macro_f1",
@@ -1741,28 +1762,6 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1819,6 +1818,17 @@
           "raw_text": "0.0381",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.012611998261547169,
           "metric_key": "macro_f1",
@@ -1841,17 +1851,6 @@
           "raw_text": "0.0098",
           "status_label": "proxy scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -1952,6 +1951,28 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.0,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.0,
+          "metric_key": "macro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.0,
+          "raw_text": "0.0000",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.0,
           "metric_key": "macro_f1",
@@ -1974,28 +1995,6 @@
           "raw_text": "0.0000",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "macro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_nano_future_window": {
           "raw": null,
           "metric_key": "macro_f1",
@@ -2052,6 +2051,28 @@
           "raw_text": "0.1659",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 0.17656983343047333,
+          "metric_key": "micro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17656983343047333,
+          "raw_text": "0.1766",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 0.17418550827844048,
+          "metric_key": "micro_f1",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.17418550827844048,
+          "raw_text": "0.1742",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 0.06469493412657774,
           "metric_key": "micro_f1",
@@ -2074,28 +2095,6 @@
           "raw_text": "0.1752",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "micro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "micro_f1",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "micro_f1",
@@ -2152,6 +2151,17 @@
           "raw_text": "0.0426",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.22941437363624573,
           "metric_key": "mae",
@@ -2174,17 +2184,6 @@
           "raw_text": "0.2530",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "mae",
@@ -2263,6 +2262,17 @@
           "raw_text": "0.2409",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": null,
+          "metric_key": "mrr",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "unsupported_without_required_target",
+          "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
+          "normalized_score": null,
+          "raw_text": "n/a",
+          "status_label": "unsupported"
+        },
         "raw128_simple": {
           "raw": 0.0026625150348991156,
           "metric_key": "mrr",
@@ -2285,17 +2295,6 @@
           "raw_text": "0.0025",
           "status_label": "proxy scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mrr",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "metadata128_neural_mlp": {
           "raw": null,
           "metric_key": "mrr",
@@ -2385,6 +2384,28 @@
           "raw_text": "134.07",
           "status_label": "scored"
         },
+        "metadata128_simple": {
+          "raw": 624.8108520507812,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.016864874132806403,
+          "raw_text": "624.81",
+          "status_label": "scored"
+        },
+        "metadata128_neural_mlp": {
+          "raw": 41.4664421081543,
+          "metric_key": "mae",
+          "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
+          "scope": "multi_episode_128_metadata_baseline",
+          "status": "scored",
+          "reason": null,
+          "normalized_score": 0.25411768748242325,
+          "raw_text": "41.47",
+          "status_label": "scored"
+        },
         "raw128_simple": {
           "raw": 52.32759475708008,
           "metric_key": "mae",
@@ -2407,28 +2428,6 @@
           "raw_text": "42.37",
           "status_label": "scored"
         },
-        "metadata128_simple": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
-        "metadata128_neural_mlp": {
-          "raw": null,
-          "metric_key": "mae",
-          "source": null,
-          "scope": "multi_episode_128_metadata_baseline",
-          "status": "not_supported_by_metadata_only_package",
-          "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required",
-          "normalized_score": null,
-          "raw_text": "n/a",
-          "status_label": "not supported"
-        },
         "cosmos3_super_reasoner": {
           "raw": null,
           "metric_key": "mae",
@@ -2459,7 +2458,7 @@
       "id": "metadata128_simple",
       "title": "128ep Metadata Simple",
       "status": "a100_rerun_pass",
-      "coverage": "20 records / 8 scored JSONL-supported axes",
+      "coverage": "20 records / 13 scored JSONL-supported axes",
       "headline": "34,269 rows; train/val/test 25,629/4,608/4,032",
       "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/summary_report.json"
     },
@@ -2467,7 +2466,7 @@
       "id": "metadata128_neural_mlp",
       "title": "128ep Metadata NN",
       "status": "a100_rerun_pass",
-      "coverage": "20 records / 8 scored JSONL-supported axes",
+      "coverage": "20 records / 13 scored JSONL-supported axes",
       "headline": "compact MLP heads over metadata/text features",
       "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/summary_report.json"
     },
@@ -4508,17 +4507,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.004579592783699693,
+      "raw_text": "0.0046",
+      "normalized_score": 0.004579592783699693,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -4526,17 +4525,17 @@
       "task_label": "Long-Horizon Next-Action Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0029821307969142615,
+      "raw_text": "0.0030",
+      "normalized_score": 0.0029821307969142615,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 13,
@@ -4670,17 +4669,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0001206030150753769,
+      "raw_text": "0.0001",
+      "normalized_score": 0.0001206030150753769,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -4688,17 +4687,17 @@
       "task_label": "Long-Horizon Next-Subtask Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 2.086049543676662e-05,
+      "raw_text": "0.0000",
+      "normalized_score": 2.086049543676662e-05,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 14,
@@ -4832,17 +4831,17 @@
       "task_label": "Interaction Text Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw annotation.hdf5 caption interaction text; the public 128 JSONL keeps only structured labels and derived metadata"
     },
     {
       "task_number": 15,
@@ -4994,17 +4993,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -5012,17 +5011,17 @@
       "task_label": "Action-Object Relation Prediction",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.0,
+      "raw_text": "0.0000",
+      "normalized_score": 0.0,
       "metric_key": "macro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 16,
@@ -5156,17 +5155,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17656983343047333,
+      "raw_text": "0.1766",
+      "normalized_score": 0.17656983343047333,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -5174,17 +5173,17 @@
       "task_label": "Future Object-Set Forecasting",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 0.17418550827844048,
+      "raw_text": "0.1742",
+      "normalized_score": 0.17418550827844048,
       "metric_key": "micro_f1",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 17,
@@ -5318,17 +5317,17 @@
       "task_label": "IMU-to-Hand Pose Reconstruction",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires raw IMU and hand-joint feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 18,
@@ -5480,17 +5479,17 @@
       "task_label": "Camera-View Synchronization Retrieval",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
+      "status": "unsupported_without_required_target",
+      "status_label": "unsupported",
       "scored": false,
       "proxy_scored": false,
       "raw": null,
       "raw_text": "n/a",
       "normalized_score": null,
       "metric_key": "mrr",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package"
     },
     {
       "task_number": 19,
@@ -5642,17 +5641,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_simple",
       "method": "128ep Metadata Simple",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 624.8108520507812,
+      "raw_text": "624.81",
+      "normalized_score": 0.016864874132806403,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,
@@ -5660,17 +5659,17 @@
       "task_label": "Time-to-Next-Transition Regression",
       "series_id": "metadata128_neural_mlp",
       "method": "128ep Metadata NN",
-      "status": "not_supported_by_metadata_only_package",
-      "status_label": "not supported",
-      "scored": false,
+      "status": "scored",
+      "status_label": "scored",
+      "scored": true,
       "proxy_scored": false,
-      "raw": null,
-      "raw_text": "n/a",
-      "normalized_score": null,
+      "raw": 41.4664421081543,
+      "raw_text": "41.47",
+      "normalized_score": 0.25411768748242325,
       "metric_key": "mae",
-      "source": null,
+      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json",
       "scope": "multi_episode_128_metadata_baseline",
-      "reason": "the 128-episode metadata/text rerun did not produce this task target; raw sensor blocks or a task-specific metadata target builder are required"
+      "reason": null
     },
     {
       "task_number": 20,

metrics/website_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-18T11:41:43+00:00",
+  "generated_at_utc": "2026-06-18T12:09:46+00:00",
   "docs_root": "docs",
   "site_base": "/ropedia-xperience-10m-task-suite/",
   "summary": {
@@ -301,7 +301,7 @@
     },
     {
       "path": "data/artifact_index.json",
-      "bytes": 116109,
+      "bytes": 116110,
       "top_level_type": "dict"
     },
     {
@@ -316,7 +316,7 @@
     },
     {
       "path": "data/episode128_task_model_radar.json",
-      "bytes": 187099,
+      "bytes": 186443,
       "top_level_type": "dict"
     },
     {
@@ -486,12 +486,12 @@
     },
     {
       "path": "data/task_method_20_gap_audit.json",
-      "bytes": 50687,
+      "bytes": 46902,
       "top_level_type": "dict"
     },
     {
       "path": "data/task_method_20_result_matrix.json",
-      "bytes": 129600,
+      "bytes": 129242,
       "top_level_type": "dict"
     },
     {
@@ -526,7 +526,7 @@
     },
     {
       "path": "data/unified_task_model_radar.json",
-      "bytes": 230951,
+      "bytes": 230297,
       "top_level_type": "dict"
     },
     {
@@ -571,7 +571,7 @@
     {
       "path": "assets/charts/episode128_task_model_radar.svg",
       "exists": true,
-      "bytes": 44825,
+      "bytes": 45937,
       "format": "SVG",
       "has_viewbox": true
     },
@@ -641,7 +641,7 @@
     {
       "path": "assets/charts/unified_task_model_radar.svg",
       "exists": true,
-      "bytes": 50841,
+      "bytes": 51953,
       "format": "SVG",
       "has_viewbox": true
     },

results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/BASELINE_ALIGNMENT_REPORT.md

@@ -27,6 +27,14 @@ The runner uses the derived Qwen JSONL export and public-safe metadata. It does
 | Cross-Modal Reconstruction | `modality_reconstruction` | unsupported_without_raw_128_feature_blocks |  | not_run |  |
 | Temporal Order Verification | `temporal_order` | pass | 0.4199 | pass | 0.8252 |
 | Multimodal Synchronization Detection | `misalignment_detection` | unsupported_without_raw_128_feature_blocks |  | not_run |  |
+| Long Horizon Next Action | `long_horizon_next_action` | pass | 0.0046 | pass | 0.0030 |
+| Next Subtask Forecast | `next_subtask_forecast` | pass | 0.0001 | pass | 0.0000 |
+| Interaction Text Prediction | `interaction_text_prediction` | unsupported_without_raw_128_feature_blocks |  | not_run |  |
+| Action Object Relation | `action_object_relation` | pass | 0.0000 | pass | 0.0000 |
+| Object Set Forecast | `object_set_forecast` | pass | 0.1766 | pass | 0.1742 |
+| Imu To Hand Pose | `imu_to_hand_pose` | unsupported_without_raw_128_feature_blocks |  | not_run |  |
+| Camera View Sync Retrieval | `camera_view_sync_retrieval` | unsupported_without_raw_128_feature_blocks |  | not_run |  |
+| Time To Transition | `time_to_transition` | pass | 624.8109 | pass | 41.4664 |
 
 ## Interpretation
 

results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json

@@ -0,0 +1,9 @@
+{
+  "status": "unsupported_without_raw_128_feature_blocks",
+  "task": "camera_view_sync_retrieval",
+  "task_display_name": "Camera View Sync Retrieval",
+  "primary_metric": "mrr",
+  "primary_score": null,
+  "reason": "requires paired camera-view feature blocks, which are not in the public 128 JSONL metadata package",
+  "source": "128_episode_qwen_jsonl_metadata"
+}

results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json

@@ -0,0 +1,188 @@
+{
+  "status": "pass",
+  "task": "long_horizon_next_action",
+  "task_display_name": "Long Horizon Next Action",
+  "model_family": "simple_centroid_metadata",
+  "source": "128_episode_qwen_jsonl_metadata",
+  "input_features": "frame/context metadata plus hashed prompt/options/main_task text; answer_json fields are excluded from inputs",
+  "split_policy": "train on train split, report val and held-out test split",
+  "num_train_windows": 25068,
+  "num_val_windows": 4496,
+  "num_test_windows": 3951,
+  "num_classes": 1211,
+  "num_train_classes": 887,
+  "majority_baseline_accuracy": 0.0,
+  "history": [
+    {
+      "method": "train_class_centroid_cosine",
+      "reason": "train_class_count=887 exceeds softmax_max_train_classes=256"
+    }
+  ],
+  "splits": {
+    "val": {
+      "accuracy": 0.027135231316725978,
+      "balanced_accuracy": 0.007303546460754275,
+      "macro_f1": 0.003918205667693489,
+      "weighted_f1": 0.015520680430211261,
+      "num_eval_windows": 4496,
+      "num_classes": 1211
+    },
+    "test": {
+      "accuracy": 0.008605416350291066,
+      "balanced_accuracy": 0.008329048558933617,
+      "macro_f1": 0.004579592783699693,
+      "weighted_f1": 0.007358915849162803,
+      "num_eval_windows": 3951,
+      "num_classes": 1211
+    }
+  },
+  "primary_metric": "macro_f1",
+  "primary_score": 0.004579592783699693,
+  "unseen_test_class_count": 144,
+  "unseen_test_classes": [
+    "Pick up dustpan",
+    "Hold container lid",
+    "Move towards the stove",
+    "Open stove pot lid",
+    "Closing the door",
+    "Picking up bottle",
+    "Wipe kitchen counter",
+    "Move towards kitchen area",
+    "Place cloth on floor",
+    "Reach for cleaning supplies",
+    "Remove cleaning bottle",
+    "Washing hands in sink",
+    "Grasping cleaning cloth",
+    "Wiping countertop",
+    "Lift pot lid",
+    "Stir contents",
+    "Place lid back",
+    "Adjust pot position",
+    "Move pot",
+    "Place towel",
+    "Start cutting",
+    "Cut along the marked line",
+    "Observe and walk through store",
+    "Inspect shelf condition",
+    "Approach boxes",
+    "Reach for wire hangers",
+    "Extract wire hangers from box",
+    "Bundle display hooks",
+    "Release hook",
+    "Move through aisle",
+    "Pick up items from the shopping bag",
+    "Place items on the shelf",
+    "Release cardboard piece and gesture",
+    "Move marker and adjust hand",
+    "Identify next cardboard piece",
+    "Observe and pause",
+    "Resume observation",
+    "Reach for next can",
+    "Hold canned food",
+    "Retrieve next canned food item",
+    "Align canned food on shelf",
+    "Retrieve canned food from box",
+    "Place another canned food on shelf",
+    "Adjust canned food on shelf",
+    "Move hand away from shelf",
+    "Hold earbud case",
+    "sort craft materials",
+    "Manipulate craft piece",
+    "Manipulate craft paper strips",
+    "Operate smartphone",
+    "Release smartphone",
+    "Sort small craft pieces",
+    "Open paper lantern",
+    "Fold paper lantern",
+    "Grasp lantern",
+    "Grasp lantern component",
+    "Align paper lantern edges",
+    "Release lantern",
+    "Pick up packaged paper lantern component",
+    "Handle paper lantern component",
+    "Open folded paper lantern",
+    "Hold paper lantern",
+    "Apply adhesive tape to lantern",
+    "Remove paper lantern part from packaging",
+    "Remove plastic packaging",
+    "Open paper lantern component",
+    "Expand paper lantern",
+    "Align edges of paper lantern",
+    "Reach for craft items",
+    "Place hand on table",
+    "Browse smartphone screen",
+    "Scroll smartphone screen",
+    "Put down smartphone",
+    "Place smartphone down",
+    "Pick up puzzle piece",
+    "Place piece into puzzle",
+    "Manipulate puzzle piece",
+    "Observe puzzle progress",
+    "Reach for puzzle piece",
+    "Attempt to fit puzzle piece",
+    "Sort puzzle pieces",
+    "Walking across the room",
+    "Approaching the table",
+    "Preparing to craft",
+    "Picking up crafting material",
+    "Manipulate material",
+    "Place material",
+    "Manipulate yellow strip",
+    "Manipulating paper strips",
+    "Manipulate bead",
+    "Manipulate beads",
+    "Hold and manipulate paper strip",
+    "Sort buttons",
+    "Arrange buttons in a line",
+    "Sort and arrange buttons",
+    "Sort button",
+    "Sort and adjust button line",
+    "Sort and place buttons",
+    "Walking in the hallway",
+    "Approaching and pressing the door switch",
+    "Entering the VR training room",
+    "Greeting/acknowledging participants",
+    "Move through the training room",
+    "Manipulate plastic strips",
+    "Manipulate plastic strip",
+    "Hold and bend plastic strip",
+    "Bend and manipulate plastic strip",
+    "Fold plastic strip",
+    "Manipulate paper decoration",
+    "Manipulate paper edge",
+    "Placing paper strip",
+    "Securing paper structure",
+    "Manipulate adhesive strip",
+    "Secure paper edges with adhesive",
+    "Record count",
+    "Sort beads and write count",
+    "Counting and organizing beads",
+    "Pick up star bead",
+    "Place and count bead",
+    "Arrange star beads",
+    "Counting star beads",
+    "Adjust paper",
+    "Gather star beads",
+    "Arrange star beads for counting",
+    "Sort and count beads",
+    "Rinse cloth in sink",
+    "Reposition hand",
+    "Walk towards other aisles",
+    "Place marked piece down",
+    "Gesturing",
+    "Reach for next canned food",
+    "Move hand away",
+    "Sort craft items",
+    "Retrieving more beads",
+    "Place smartphone on stand",
+    "Move dustpan to side",
+    "Walking towards door",
+    "Grasp cleaning bottle",
+    "Observe colleague and workspace",
+    "Open earbud case",
+    "Adjust lantern string",
+    "Adjust lantern shape",
+    "Pick up small piece of material",
+    "Use phone while crafting"
+  ]
+}

results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/per_class_metrics.csv

@@ -0,0 +1,1212 @@
+class_id,class_name,support,predicted,precision,recall,f1
+0,Place jar on shelf,0,0,0.0,0.0,0.0
+1,Reach for item in box,0,1,0.0,0.0,0.0
+2,Pick up product from box,0,1,0.0,0.0,0.0
+3,Place product on shelf,0,151,0.0,0.0,0.0
+4,Pick up product from bin,0,6,0.0,0.0,0.0
+5,Reach for next product,0,0,0.0,0.0,0.0
+6,Place canned product on shelf,0,0,0.0,0.0,0.0
+7,Pick up canned product,0,0,0.0,0.0,0.0
+8,Arrange canned products on shelf,0,0,0.0,0.0,0.0
+9,Move bin to shelf area,0,0,0.0,0.0,0.0
+10,Place can on shelf,20,0,0.0,0.0,0.0
+11,Retract hand,0,1,0.0,0.0,0.0
+12,Hold and wipe product,0,0,0.0,0.0,0.0
+13,Wipe down shelf,0,0,0.0,0.0,0.0
+14,Pick up product,0,6,0.0,0.0,0.0
+15,Wipe product,0,7,0.0,0.0,0.0
+16,Wipe food product,0,4,0.0,0.0,0.0
+17,Reach into box,9,2,0.0,0.0,0.0
+18,Wipe jar,0,0,0.0,0.0,0.0
+19,Wipe shelf,0,1,0.0,0.0,0.0
+20,Hold pickle jar,0,0,0.0,0.0,0.0
+21,Release pickle jar,0,0,0.0,0.0,0.0
+22,Hold cleaning cloth,0,1,0.0,0.0,0.0
+23,Wipe the shelf,0,0,0.0,0.0,0.0
+24,Wipe the product jar,0,0,0.0,0.0,0.0
+25,Move to next section,0,10,0.0,0.0,0.0
+26,Place product in box,0,0,0.0,0.0,0.0
+27,Hold product,0,2,0.0,0.0,0.0
+28,Hold item and adjust posture,0,1,0.0,0.0,0.0
+29,Grasp product from box,0,0,0.0,0.0,0.0
+30,Prepare to place product,0,1,0.0,0.0,0.0
+31,Move product to shelf,0,0,0.0,0.0,0.0
+32,Move product to box,0,1,0.0,0.0,0.0
+33,Grasp next item,0,0,0.0,0.0,0.0
+34,Align button in row,0,1,0.0,0.0,0.0
+35,Pick up button,9,1,0.0,0.0,0.0
+36,Place button in row,0,0,0.0,0.0,0.0
+37,Align button,0,0,0.0,0.0,0.0
+38,Arrange button cluster,0,0,0.0,0.0,0.0
+39,Align button row,0,1,0.0,0.0,0.0
+40,Arrange buttons on table,0,0,0.0,0.0,0.0
+41,Adjust red button in row,0,1,0.0,0.0,0.0
+42,Select button from pile,0,5,0.0,0.0,0.0
+43,Adjust red button,0,0,0.0,0.0,0.0
+44,Pull back hand,0,0,0.0,0.0,0.0
+45,Survey the table,0,2,0.0,0.0,0.0
+46,Arrange black buttons,0,3,0.0,0.0,0.0
+47,Pick up black button,0,0,0.0,0.0,0.0
+48,Move black button,0,0,0.0,0.0,0.0
+49,Pick up red button,0,0,0.0,0.0,0.0
+50,Reach for multicolored buttons,0,3,0.0,0.0,0.0
+51,Arrange buttons in row,0,0,0.0,0.0,0.0
+52,Touch device,0,0,0.0,0.0,0.0
+53,Align red button in row,0,0,0.0,0.0,0.0
+54,Reach and sort buttons,0,0,0.0,0.0,0.0
+55,Reach for button,0,0,0.0,0.0,0.0
+56,Place button,31,0,0.0,0.0,0.0
+57,Cut cardboard piece,40,0,0.0,0.0,0.0
+58,Manipulate cardboard piece,0,1,0.0,0.0,0.0
+59,Position scissors to cut cardboard,0,0,0.0,0.0,0.0
+60,Cut cardboard,174,231,0.021645021645021644,0.028735632183908046,0.024691358024691357
+61,Release scissors,4,1,0.0,0.0,0.0
+62,Position scissors,0,0,0.0,0.0,0.0
+63,Pick up scissors,0,0,0.0,0.0,0.0
+64,Move away from workstation,0,0,0.0,0.0,0.0
+65,Walk through corridor,0,0,0.0,0.0,0.0
+66,Mark cardboard with ruler and pen,0,0,0.0,0.0,0.0
+67,Mark cardboard with pen and ruler,0,0,0.0,0.0,0.0
+68,Cut cardboard with scissors,0,0,0.0,0.0,0.0
+69,Place down scissors,0,0,0.0,0.0,0.0
+70,Position ruler on cardboard,0,1,0.0,0.0,0.0
+71,Hold ruler steady,0,0,0.0,0.0,0.0
+72,Mark line on cardboard,0,2,0.0,0.0,0.0
+73,Move marker and ruler,0,0,0.0,0.0,0.0
+74,Pick up smartphone,6,4,0.0,0.0,0.0
+75,Mark cardboard,0,0,0.0,0.0,0.0
+76,Hold cardboard pieces,0,0,0.0,0.0,0.0
+77,Place cardboard,0,1,0.0,0.0,0.0
+78,Align ruler on cardboard,0,9,0.0,0.0,0.0
+79,Mark cardboard with pen,0,0,0.0,0.0,0.0
+80,Plug cable into portable charger,0,0,0.0,0.0,0.0
+81,Pick up portable charger,0,0,0.0,0.0,0.0
+82,Walk towards room,0,0,0.0,0.0,0.0
+83,Hold portable charger,0,0,0.0,0.0,0.0
+84,Place charger on table,0,0,0.0,0.0,0.0
+85,Hold charger and cable,0,0,0.0,0.0,0.0
+86,Manipulate power cable plug,0,0,0.0,0.0,0.0
+87,Insert plug into power adapter,0,0,0.0,0.0,0.0
+88,Hold power adapter,0,0,0.0,0.0,0.0
+89,Align charging cable,0,0,0.0,0.0,0.0
+90,Insert charging cable,0,0,0.0,0.0,0.0
+91,Observe desktop layout,0,0,0.0,0.0,0.0
+92,Retract camera/reposition view,0,0,0.0,0.0,0.0
+93,Manipulate paper strip,152,0,0.0,0.0,0.0
+94,Fold paper strip,0,313,0.0,0.0,0.0
+95,Pick up yellow paper strip,0,0,0.0,0.0,0.0
+96,Pick up phone,0,4,0.0,0.0,0.0
+97,Use phone,31,12,0.0,0.0,0.0
+98,Place phone on desk,0,2,0.0,0.0,0.0
+99,Interact with phone,0,1,0.0,0.0,0.0
+100,Place phone down,11,4,0.0,0.0,0.0
+101,Adjust paper strip,0,10,0.0,0.0,0.0
+102,Release folded paper,0,4,0.0,0.0,0.0
+103,Fold paper strip into knot,0,0,0.0,0.0,0.0
+104,Fold paper strip into lucky star,0,0,0.0,0.0,0.0
+105,Inflate paper star,0,0,0.0,0.0,0.0
+106,Fold purple paper strip,0,0,0.0,0.0,0.0
+107,Fold purple paper,0,0,0.0,0.0,0.0
+108,Hold and crease purple paper,0,1,0.0,0.0,0.0
+109,Release paper,0,0,0.0,0.0,0.0
+110,Reach for phone,0,0,0.0,0.0,0.0
+111,Retrieve paper strips,0,0,0.0,0.0,0.0
+112,Fold and organize paper strips,0,2,0.0,0.0,0.0
+113,Hold charger,0,0,0.0,0.0,0.0
+114,Separate cardboard piece,0,0,0.0,0.0,0.0
+115,Cut cardboard with utility knife,0,0,0.0,0.0,0.0
+116,Mark cardboard piece,85,0,0.0,0.0,0.0
+117,Retract hand from bag,0,5,0.0,0.0,0.0
+118,Open small case,0,2,0.0,0.0,0.0
+119,Measure cardboard with ruler,0,2,0.0,0.0,0.0
+120,Move smartphone,28,1,0.0,0.0,0.0
+121,Hold ruler on cardboard,0,3,0.0,0.0,0.0
+122,Remove ruler,0,0,0.0,0.0,0.0
+123,Walk towards table,0,0,0.0,0.0,0.0
+124,Approach desk,0,0,0.0,0.0,0.0
+125,Position hands for work,0,1,0.0,0.0,0.0
+126,Manipulate quilling strip,0,0,0.0,0.0,0.0
+127,Release quilling strip,0,0,0.0,0.0,0.0
+128,Release paper strip,35,0,0.0,0.0,0.0
+129,Begin rolling quilling strip,0,1,0.0,0.0,0.0
+130,Type on smartphone,0,26,0.0,0.0,0.0
+131,Use phone to check stock,0,0,0.0,0.0,0.0
+132,Grasp package,0,1,0.0,0.0,0.0
+133,Place item on shelf,23,109,0.0,0.0,0.0
+134,Observe shelf status,0,2,0.0,0.0,0.0
+135,Walk towards aisle,0,3,0.0,0.0,0.0
+136,Move towards shelf,0,1,0.0,0.0,0.0
+137,Adjust item on shelf,26,0,0.0,0.0,0.0
+138,Reach for another item,18,1,0.0,0.0,0.0
+139,Remove item from shelf,0,0,0.0,0.0,0.0
+140,Discard item into bin,0,3,0.0,0.0,0.0
+141,Sweep debris,0,8,0.0,0.0,0.0
+142,Touch shelf edge,0,1,0.0,0.0,0.0
+143,Reach for product,0,0,0.0,0.0,0.0
+144,Release label,0,0,0.0,0.0,0.0
+145,Remove shelf label,0,1,0.0,0.0,0.0
+146,Move along shelf,0,0,0.0,0.0,0.0
+147,Carry stool to next shelf,0,0,0.0,0.0,0.0
+148,Place stool on floor,0,1,0.0,0.0,0.0
+149,Observe shelf,0,2,0.0,0.0,0.0
+150,Walk towards next aisle,0,0,0.0,0.0,0.0
+151,Reach for product labels,0,0,0.0,0.0,0.0
+152,Hold product labels,0,3,0.0,0.0,0.0
+153,Examine labels,0,0,0.0,0.0,0.0
+154,Place sauce in container,0,0,0.0,0.0,0.0
+155,Pick up supplement bottle,0,0,0.0,0.0,0.0
+156,Hold supplement bottle,0,0,0.0,0.0,0.0
+157,Open supplement bottle,0,0,0.0,0.0,0.0
+158,Walk through store,0,0,0.0,0.0,0.0
+159,Reach for item on shelf,0,0,0.0,0.0,0.0
+160,Examine item,0,0,0.0,0.0,0.0
+161,Place item in container,0,0,0.0,0.0,0.0
+162,Pick up another item,0,1,0.0,0.0,0.0
+163,Pick up oil bottle,0,0,0.0,0.0,0.0
+164,Place oil in container,0,0,0.0,0.0,0.0
+165,Inspect supplement bottle,0,3,0.0,0.0,0.0
+166,Place supplement bottle in container,0,0,0.0,0.0,0.0
+167,Pick up spice jar,0,0,0.0,0.0,0.0
+168,Place spice jar in container,0,0,0.0,0.0,0.0
+169,Sort beads,16,74,0.0,0.0,0.0
+170,Adjust hand position,0,0,0.0,0.0,0.0
+171,Arrange star-shaped beads,0,0,0.0,0.0,0.0
+172,Move pen,0,1,0.0,0.0,0.0
+173,Sort beads by color,0,12,0.0,0.0,0.0
+174,Move towards table,0,0,0.0,0.0,0.0
+175,Observe room,0,1,0.0,0.0,0.0
+176,Check watch,0,2,0.0,0.0,0.0
+177,Prepare to sort beads,0,1,0.0,0.0,0.0
+178,Align ruler,0,0,0.0,0.0,0.0
+179,Adjust grip,0,1,0.0,0.0,0.0
+180,Move ruler,0,0,0.0,0.0,0.0
+181,Adjust ruler position,0,0,0.0,0.0,0.0
+182,Mark cardboard with marker,0,0,0.0,0.0,0.0
+183,Draw lines on cardboard,0,1,0.0,0.0,0.0
+184,Drawing lines on cardboard,0,0,0.0,0.0,0.0
+185,Reposition marker,0,0,0.0,0.0,0.0
+186,Mark lines with marker,0,0,0.0,0.0,0.0
+187,Position the ruler,0,0,0.0,0.0,0.0
+188,Stack cardboard pieces,0,0,0.0,0.0,0.0
+189,Walking in the workspace,0,0,0.0,0.0,0.0
+190,Insert charging cable into power bank,0,0,0.0,0.0,0.0
+191,Manipulate and inspect colorful pieces,0,0,0.0,0.0,0.0
+192,Manipulate colorful pieces,0,0,0.0,0.0,0.0
+193,Sort colorful pieces,0,0,0.0,0.0,0.0
+194,Hold power bank and cable,0,0,0.0,0.0,0.0
+195,Touch pieces in box,0,0,0.0,0.0,0.0
+196,Hold small white box,0,1,0.0,0.0,0.0
+197,Place white box on table,0,0,0.0,0.0,0.0
+198,Adjust smartphone and sort pieces,0,0,0.0,0.0,0.0
+199,Sort small colorful pieces,0,1,0.0,0.0,0.0
+200,Sorting colorful paper pieces,0,0,0.0,0.0,0.0
+201,Use phone to check instructions,0,31,0.0,0.0,0.0
+202,Trace pattern on cardboard,0,4,0.0,0.0,0.0
+203,Remove cardboard pattern,0,7,0.0,0.0,0.0
+204,Remove cardboard pattern piece,0,2,0.0,0.0,0.0
+205,Cut out cardboard pattern,0,9,0.0,0.0,0.0
+206,Cut cardboard pattern,0,12,0.0,0.0,0.0
+207,Adjust cardboard position,0,4,0.0,0.0,0.0
+208,Interact with smartphone screen,0,1,0.0,0.0,0.0
+209,Pick up metal ruler,0,0,0.0,0.0,0.0
+210,Pick up pen,8,0,0.0,0.0,0.0
+211,Move pen aside,0,9,0.0,0.0,0.0
+212,Reposition and cut,0,0,0.0,0.0,0.0
+213,Hold quilling paper,0,0,0.0,0.0,0.0
+214,Roll quilling paper,0,0,0.0,0.0,0.0
+215,Release paper coil,0,3,0.0,0.0,0.0
+216,Pick up paper strip,0,1,0.0,0.0,0.0
+217,Manipulate quilled paper strip,0,0,0.0,0.0,0.0
+218,Release and prepare new strip,0,0,0.0,0.0,0.0
+219,Manipulate small paper segment,0,1,0.0,0.0,0.0
+220,Place down paper segment,0,2,0.0,0.0,0.0
+221,Reach for paper strips,0,1,0.0,0.0,0.0
+222,Browse and interact with phone interface,0,4,0.0,0.0,0.0
+223,Interacting with phone screen,0,0,0.0,0.0,0.0
+224,Pick up light blue strip,0,8,0.0,0.0,0.0
+225,Inspect strip,0,0,0.0,0.0,0.0
+226,Manipulate light blue strip,0,1,0.0,0.0,0.0
+227,Cut cardboard tube,0,2,0.0,0.0,0.0
+228,Stacking cardboard pieces,0,14,0.0,0.0,0.0
+229,Moving hand,0,0,0.0,0.0,0.0
+230,Position cardboard for cutting,0,0,0.0,0.0,0.0
+231,Place cardboard piece,0,0,0.0,0.0,0.0
+232,Pick up cardboard piece,0,0,0.0,0.0,0.0
+233,Cut cardboard piece with scissors,0,0,0.0,0.0,0.0
+234,Release cardboard piece,0,4,0.0,0.0,0.0
+235,Walk across office,0,0,0.0,0.0,0.0
+236,Cut cardboard into triangles,0,0,0.0,0.0,0.0
+237,Cut cardboard shape,0,53,0.0,0.0,0.0
+238,Pick up cardboard cutout,0,9,0.0,0.0,0.0
+239,Walk with cardboard cutout,0,0,0.0,0.0,0.0
+240,Approach workstation,0,4,0.0,0.0,0.0
+241,Organize tools and materials,0,0,0.0,0.0,0.0
+242,Cut cardboard triangle,0,0,0.0,0.0,0.0
+243,Holding marker,0,32,0.0,0.0,0.0
+244,Lift utility knife,0,0,0.0,0.0,0.0
+245,Inspect cardboard piece,0,0,0.0,0.0,0.0
+246,Position cardboard piece,0,0,0.0,0.0,0.0
+247,Align scissors,0,0,0.0,0.0,0.0
+248,Cut cardboard strip,0,0,0.0,0.0,0.0
+249,Position cardboard strip,0,4,0.0,0.0,0.0
+250,Inspect cardboard strip,0,0,0.0,0.0,0.0
+251,Align cardboard piece,0,0,0.0,0.0,0.0
+252,Complete the cut,0,0,0.0,0.0,0.0
+253,Put down utility knife,0,1,0.0,0.0,0.0
+254,Fold cardboard,0,10,0.0,0.0,0.0
+255,Pick up utility knife,18,0,0.0,0.0,0.0
+256,Hold utility knife,0,1,0.0,0.0,0.0
+257,Pick up cardboard strip,0,0,0.0,0.0,0.0
+258,Place cardboard strip,0,2,0.0,0.0,0.0
+259,Place cans into box,0,0,0.0,0.0,0.0
+260,Arrange cans in box,0,0,0.0,0.0,0.0
+261,Reach for can,0,0,0.0,0.0,0.0
+262,Arrange cans on shelf,0,3,0.0,0.0,0.0
+263,Reach for additional items,0,0,0.0,0.0,0.0
+264,Reach for container,0,3,0.0,0.0,0.0
+265,Adjust position,0,1,0.0,0.0,0.0
+266,Prepare to pick up item,0,0,0.0,0.0,0.0
+267,Place container in bin,0,0,0.0,0.0,0.0
+268,Adjust cans in bin,0,0,0.0,0.0,0.0
+269,Hold and inspect can,0,2,0.0,0.0,0.0
+270,Adjust perspective,0,1,0.0,0.0,0.0
+271,Inspect shelf and organize stock,0,0,0.0,0.0,0.0
+272,Placing stock on shelf,0,10,0.0,0.0,0.0
+273,Hold small product bag,0,12,0.0,0.0,0.0
+274,Position shelving divider,0,2,0.0,0.0,0.0
+275,Move away from shelf,0,0,0.0,0.0,0.0
+276,Pick up container,0,4,0.0,0.0,0.0
+277,Pick up cleaning cloth,0,1,0.0,0.0,0.0
+278,Pick up product box,0,4,0.0,0.0,0.0
+279,Place box on shelf,0,8,0.0,0.0,0.0
+280,Reach for next item,9,3,0.0,0.0,0.0
+281,Place plush toy on shelf,0,2,0.0,0.0,0.0
+282,Adjust placement on shelf,0,2,0.0,0.0,0.0
+283,Move plush toy,0,1,0.0,0.0,0.0
+284,Reach for product on shelf,0,0,0.0,0.0,0.0
+285,Hold cardboard,0,0,0.0,0.0,0.0
+286,Arrange cardboard,0,0,0.0,0.0,0.0
+287,Walk with marker,0,0,0.0,0.0,0.0
+288,Pick up small object,0,0,0.0,0.0,0.0
+289,Walk across room,0,0,0.0,0.0,0.0
+290,Place cardboard square on stack,0,0,0.0,0.0,0.0
+291,Arrange cardboard squares,0,0,0.0,0.0,0.0
+292,Stacking cardboard squares,0,0,0.0,0.0,0.0
+293,Stacking cardboard square,0,0,0.0,0.0,0.0
+294,Stack cardboard square,0,0,0.0,0.0,0.0
+295,Stack cardboard squares,0,0,0.0,0.0,0.0
+296,Sorting paper stars,0,0,0.0,0.0,0.0
+297,Place star,0,0,0.0,0.0,0.0
+298,Sort paper star,0,24,0.0,0.0,0.0
+299,Sort paper stars,0,2,0.0,0.0,0.0
+300,Place paper star,0,0,0.0,0.0,0.0
+301,Walk away,0,1,0.0,0.0,0.0
+302,Open door,0,1,0.0,0.0,0.0
+303,Walk through doorway,0,2,0.0,0.0,0.0
+304,Pick up object,0,0,0.0,0.0,0.0
+305,Place item on table,0,4,0.0,0.0,0.0
+306,Move phone,24,1,0.0,0.0,0.0
+307,Sort and place paper star,0,0,0.0,0.0,0.0
+308,Hold cardboard strip,0,0,0.0,0.0,0.0
+309,Align cardboard strip,0,1,0.0,0.0,0.0
+310,Hold cardboard with ruler,0,0,0.0,0.0,0.0
+311,Move utility knife along ruler,0,0,0.0,0.0,0.0
+312,Slide utility knife along ruler,0,0,0.0,0.0,0.0
+313,Guide utility knife along ruler,0,0,0.0,0.0,0.0
+314,Draw line on cardboard,0,0,0.0,0.0,0.0
+315,Marking lines on cardboard,0,0,0.0,0.0,0.0
+316,Hold craft tool,0,9,0.0,0.0,0.0
+317,Approach table,0,12,0.0,0.0,0.0
+318,Place tool on table,0,3,0.0,0.0,0.0
+319,Move hand toward craft materials,0,17,0.0,0.0,0.0
+320,Manipulate paper strips,0,58,0.0,0.0,0.0
+321,Pick up blue paper strip,0,7,0.0,0.0,0.0
+322,Hold and bend paper strip,0,8,0.0,0.0,0.0
+323,Hold small object,0,8,0.0,0.0,0.0
+324,Move hand away from workspace,0,6,0.0,0.0,0.0
+325,Observe workspace,13,53,0.0,0.0,0.0
+326,Place puzzle piece,21,69,0.0,0.0,0.0
+327,Release puzzle piece,4,3,0.0,0.0,0.0
+328,Scan for next piece,0,21,0.0,0.0,0.0
+329,Positioning puzzle piece,0,6,0.0,0.0,0.0
+330,Manipulate puzzle pieces,35,24,0.0,0.0,0.0
+331,Adjust puzzle piece,11,152,0.07236842105263158,1.0,0.13496932515337423
+332,Adjusting puzzle piece,0,2,0.0,0.0,0.0
+333,Adjusting a puzzle piece,0,0,0.0,0.0,0.0
+334,Draw line along ruler,0,0,0.0,0.0,0.0
+335,Reposition ruler,0,0,0.0,0.0,0.0
+336,Hold ruler and pen steady,0,0,0.0,0.0,0.0
+337,Mark lines on cardboard,0,0,0.0,0.0,0.0
+338,Place marker down,0,0,0.0,0.0,0.0
+339,Walk across the room,0,0,0.0,0.0,0.0
+340,Approach packing area,0,0,0.0,0.0,0.0
+341,Pack beads into box,0,0,0.0,0.0,0.0
+342,Pick up beads,0,0,0.0,0.0,0.0
+343,Deposit beads into box,0,0,0.0,0.0,0.0
+344,Pick up cardboard tray,0,0,0.0,0.0,0.0
+345,Move tray towards packing area,0,3,0.0,0.0,0.0
+346,Position cardboard tray,0,0,0.0,0.0,0.0
+347,Cut light green fabric,0,0,0.0,0.0,0.0
+348,Continue cutting fabric,0,1,0.0,0.0,0.0
+349,Cut fabric with scissors,0,1,0.0,0.0,0.0
+350,Adjusting fabric for cutting,0,0,0.0,0.0,0.0
+351,Cutting fabric,0,0,0.0,0.0,0.0
+352,Mark fabric with pen,0,0,0.0,0.0,0.0
+353,Mark fabric,0,4,0.0,0.0,0.0
+354,Mark fabric with pen and ruler,0,0,0.0,0.0,0.0
+355,Carry cardboard piece,0,0,0.0,0.0,0.0
+356,Pick up electronic accessory from box,0,0,0.0,0.0,0.0
+357,Place accessory on shelf,0,0,0.0,0.0,0.0
+358,Pick up accessory,0,0,0.0,0.0,0.0
+359,Reach towards shelf,0,0,0.0,0.0,0.0
+360,Place accessory into box,0,0,0.0,0.0,0.0
+361,Pick up new electronic product,0,0,0.0,0.0,0.0
+362,Pick up electronic product,0,0,0.0,0.0,0.0
+363,Move hand back to box,0,0,0.0,0.0,0.0
+364,Move product towards shelf,0,0,0.0,0.0,0.0
+365,Walk with shopping bag,0,0,0.0,0.0,0.0
+366,Pick up item from box,0,0,0.0,0.0,0.0
+367,Move towards box,0,9,0.0,0.0,0.0
+368,Hold items,0,4,0.0,0.0,0.0
+369,Place items on shelf,0,8,0.0,0.0,0.0
+370,Move to box,0,4,0.0,0.0,0.0
+371,Move box to next position,0,2,0.0,0.0,0.0
+372,Hold snack package,0,0,0.0,0.0,0.0
+373,Place snack package on shelf,0,0,0.0,0.0,0.0
+374,Place snack package in box,0,0,0.0,0.0,0.0
+375,Hold snack packages,0,2,0.0,0.0,0.0
+376,Pick up snack packages,0,13,0.0,0.0,0.0
+377,Walk towards shelves,9,1,0.0,0.0,0.0
+378,Pick up snack package,0,8,0.0,0.0,0.0
+379,Organize snacks in box,0,0,0.0,0.0,0.0
+380,Adjust snack package,0,6,0.0,0.0,0.0
+381,Open cardboard box,0,5,0.0,0.0,0.0
+382,Remove cardboard flap,0,2,0.0,0.0,0.0
+383,Align plastic containers,0,0,0.0,0.0,0.0
+384,Reach for items,0,0,0.0,0.0,0.0
+385,Adjust containers on shelf,0,0,0.0,0.0,0.0
+386,Adjust container position,0,0,0.0,0.0,0.0
+387,Withdraw hand,0,0,0.0,0.0,0.0
+388,Place container on shelf,0,0,0.0,0.0,0.0
+389,Place item in shopping bag,0,1,0.0,0.0,0.0
+390,Grasp item,0,0,0.0,0.0,0.0
+391,Move item to bag,0,0,0.0,0.0,0.0
+392,Pick up plush toy,0,0,0.0,0.0,0.0
+393,Place plush toy into bag,0,0,0.0,0.0,0.0
+394,Grasp shopping bag,0,2,0.0,0.0,0.0
+395,Prepare to place item in bag,0,0,0.0,0.0,0.0
+396,Organize bag contents,0,0,0.0,0.0,0.0
+397,Grasp and retrieve item,0,0,0.0,0.0,0.0
+398,Place item into shopping bag,0,0,0.0,0.0,0.0
+399,Sort star-shaped beads,16,0,0.0,0.0,0.0
+400,Sort beads on the table,0,0,0.0,0.0,0.0
+401,Sort beads on table,0,0,0.0,0.0,0.0
+402,Hold instructional sign,0,1,0.0,0.0,0.0
+403,Pick up star-shaped bead,0,17,0.0,0.0,0.0
+404,Place bead on table,0,1,0.0,0.0,0.0
+405,Reposition sign and organize beads,0,9,0.0,0.0,0.0
+406,Reposition ruler and pen,0,0,0.0,0.0,0.0
+407,Reposition pen and prepare for next line,0,0,0.0,0.0,0.0
+408,Draw straight lines on cardboard,0,0,0.0,0.0,0.0
+409,Draw lines with ruler,0,0,0.0,0.0,0.0
+410,Sort origami stars,0,0,0.0,0.0,0.0
+411,Walk in hallway,0,0,0.0,0.0,0.0
+412,Reach for stars,0,0,0.0,0.0,0.0
+413,Walk towards desk,0,0,0.0,0.0,0.0
+414,Grasp origami stars,0,0,0.0,0.0,0.0
+415,Place stars in container,0,1,0.0,0.0,0.0
+416,Sort light blue origami stars,0,0,0.0,0.0,0.0
+417,Sort origami stars by color,0,0,0.0,0.0,0.0
+418,Move origami stars,0,0,0.0,0.0,0.0
+419,Put down scissors,0,0,0.0,0.0,0.0
+420,Use smartphone,70,0,0.0,0.0,0.0
+421,Pick up water bottle,0,4,0.0,0.0,0.0
+422,Hold water bottle,0,0,0.0,0.0,0.0
+423,Place water bottle on table,0,0,0.0,0.0,0.0
+424,Hold phone,0,0,0.0,0.0,0.0
+425,Hold and view phone,0,0,0.0,0.0,0.0
+426,Cut cardboard pieces with scissors,0,30,0.0,0.0,0.0
+427,Vacuum the carpet,0,0,0.0,0.0,0.0
+428,Push vacuum cleaner,0,0,0.0,0.0,0.0
+429,Adjust vacuum cleaner position,0,0,0.0,0.0,0.0
+430,Vacuuming carpet edge,0,1,0.0,0.0,0.0
+431,Vacuum edge of carpet,0,0,0.0,0.0,0.0
+432,Vacuuming carpet corner,0,2,0.0,0.0,0.0
+433,Vacuuming the carpet edge,0,0,0.0,0.0,0.0
+434,Move vacuum cleaner,0,0,0.0,0.0,0.0
+435,Vacuuming along the wall edge,0,0,0.0,0.0,0.0
+436,Fold paper strip into star,0,0,0.0,0.0,0.0
+437,Arrange Mahjong tiles,0,0,0.0,0.0,0.0
+438,Rearrange Mahjong tiles,0,0,0.0,0.0,0.0
+439,Adjust Mahjong tiles,0,0,0.0,0.0,0.0
+440,Reach for Mahjong tiles,0,0,0.0,0.0,0.0
+441,Rearrange Mahjong tile,0,2,0.0,0.0,0.0
+442,Adjust Mahjong tile,0,0,0.0,0.0,0.0
+443,Align Mahjong tiles,0,0,0.0,0.0,0.0
+444,Move Mahjong tile,0,0,0.0,0.0,0.0
+445,Realign Mahjong tiles,0,2,0.0,0.0,0.0
+446,Cut cardboard square,0,0,0.0,0.0,0.0
+447,Trim cardboard piece,0,0,0.0,0.0,0.0
+448,Pick up cereal boxes,0,0,0.0,0.0,0.0
+449,Carry cereal boxes,0,6,0.0,0.0,0.0
+450,Carry cereal towards aisle,0,6,0.0,0.0,0.0
+451,Carry pasta box towards aisle,0,2,0.0,0.0,0.0
+452,Pick up container from box,0,3,0.0,0.0,0.0
+453,Hold container,0,144,0.0,0.0,0.0
+454,Reach for items in box,0,3,0.0,0.0,0.0
+455,Pick up grocery item,0,8,0.0,0.0,0.0
+456,Carry item to shelf,0,3,0.0,0.0,0.0
+457,Move to stock products,0,1,0.0,0.0,0.0
+458,Wipe shelf surface,0,0,0.0,0.0,0.0
+459,Move cardboard box,0,0,0.0,0.0,0.0
+460,Place snack on shelf,0,0,0.0,0.0,0.0
+461,Retrieve snack from container,0,0,0.0,0.0,0.0
+462,Pick up gift box,0,0,0.0,0.0,0.0
+463,Pick up next gift box,0,0,0.0,0.0,0.0
+464,Pick up snack pouch,0,1,0.0,0.0,0.0
+465,Place snack pouch in container,0,0,0.0,0.0,0.0
+466,Reach for snack pouch,0,0,0.0,0.0,0.0
+467,Move storage bin,0,0,0.0,0.0,0.0
+468,Reach for shelf,0,0,0.0,0.0,0.0
+469,Hold bin and move through aisle,0,0,0.0,0.0,0.0
+470,Remove storage bin from shelf,0,1,0.0,0.0,0.0
+471,Reach for empty shelf space,0,0,0.0,0.0,0.0
+472,Grasp plastic bag on shelf,0,0,0.0,0.0,0.0
+473,Remove plastic container from shelf,0,261,0.0,0.0,0.0
+474,Arrange plastic containers,0,0,0.0,0.0,0.0
+475,Retrieve another container,0,0,0.0,0.0,0.0
+476,Arrange container on shelf,0,0,0.0,0.0,0.0
+477,Hold smartphone,42,0,0.0,0.0,0.0
+478,Place smartphone on desk,0,0,0.0,0.0,0.0
+479,Reach for water bottle,0,0,0.0,0.0,0.0
+480,Hold scissors,0,0,0.0,0.0,0.0
+481,Cut newspaper,0,0,0.0,0.0,0.0
+482,Continue cutting newspaper,0,0,0.0,0.0,0.0
+483,Place scissors on table,0,0,0.0,0.0,0.0
+484,Move scissors away,0,0,0.0,0.0,0.0
+485,Place scissors down,0,0,0.0,0.0,0.0
+486,Arrange tiles into row,0,0,0.0,0.0,0.0
+487,Adjust tile row alignment,0,0,0.0,0.0,0.0
+488,Adjust Mahjong tile alignment,0,0,0.0,0.0,0.0
+489,Adjust Mahjong tile on the stack,0,0,0.0,0.0,0.0
+490,Pick up Mahjong tile,0,0,0.0,0.0,0.0
+491,Place Mahjong tile on the stack,0,0,0.0,0.0,0.0
+492,Place Mahjong tile on stack,0,0,0.0,0.0,0.0
+493,Hold ruler and draw line,0,0,0.0,0.0,0.0
+494,Draw line,0,0,0.0,0.0,0.0
+495,Mark lines with pen along ruler,0,0,0.0,0.0,0.0
+496,Hold ruler and mark cardboard,0,0,0.0,0.0,0.0
+497,Hold ruler and marker,0,0,0.0,0.0,0.0
+498,Inspect charging case,0,14,0.0,0.0,0.0
+499,Place charging case down,0,0,0.0,0.0,0.0
+500,Hold paper strip,0,0,0.0,0.0,0.0
+501,Measure and mark cardboard,0,0,0.0,0.0,0.0
+502,Hold and align cardboard,0,0,0.0,0.0,0.0
+503,Position cardboard tube,0,0,0.0,0.0,0.0
+504,Cut cardboard strip with scissors,0,0,0.0,0.0,0.0
+505,Scroll on smartphone,0,0,0.0,0.0,0.0
+506,Tap smartphone screen,0,0,0.0,0.0,0.0
+507,Scroll through photo gallery,0,0,0.0,0.0,0.0
+508,Typing message on smartphone,0,0,0.0,0.0,0.0
+509,Typing on smartphone,0,0,0.0,0.0,0.0
+510,Tapping smartphone screen,0,0,0.0,0.0,0.0
+511,Putting away smartphone,0,0,0.0,0.0,0.0
+512,Stop measuring and put down tools,0,0,0.0,0.0,0.0
+513,Draw line with pen,0,0,0.0,0.0,0.0
+514,Prepare to draw lines,0,1,0.0,0.0,0.0
+515,Remove ruler and marker,0,1,0.0,0.0,0.0
+516,Align ruler and mark cardboard,0,0,0.0,0.0,0.0
+517,Walking through classroom,0,0,0.0,0.0,0.0
+518,Assemble cardboard pieces,0,0,0.0,0.0,0.0
+519,Move marker away,0,0,0.0,0.0,0.0
+520,Arrange cardboard piece,0,0,0.0,0.0,0.0
+521,Position ruler and mark cardboard,0,0,0.0,0.0,0.0
+522,Place canned good on shelf,0,0,0.0,0.0,0.0
+523,Move canned goods container,0,0,0.0,0.0,0.0
+524,Position container near shelf,0,0,0.0,0.0,0.0
+525,Adjust container on shelf,0,0,0.0,0.0,0.0
+526,Pick up canned food,13,0,0.0,0.0,0.0
+527,Place canned food in container,0,0,0.0,0.0,0.0
+528,Adjust cans in container,0,0,0.0,0.0,0.0
+529,Adjust cans in tray,0,0,0.0,0.0,0.0
+530,Adjusting canned goods on shelf,0,0,0.0,0.0,0.0
+531,Align canned goods on shelf,0,0,0.0,0.0,0.0
+532,Place canned food on shelf,69,0,0.0,0.0,0.0
+533,Reach for next canned food item,0,0,0.0,0.0,0.0
+534,Wipe the plastic jar,0,195,0.0,0.0,0.0
+535,Finish wiping and inspect jar,0,1,0.0,0.0,0.0
+536,Inspect jar,0,18,0.0,0.0,0.0
+537,Pick up tin can,0,0,0.0,0.0,0.0
+538,Hold items and inspect shelf,0,58,0.0,0.0,0.0
+539,Move cardboard,0,3,0.0,0.0,0.0
+540,Stabilize cardboard,0,6,0.0,0.0,0.0
+541,Stabilize ruler,0,3,0.0,0.0,0.0
+542,Labeling cardboard squares,0,15,0.0,0.0,0.0
+543,Moving cardboard square,0,1,0.0,0.0,0.0
+544,Labeling cardboard square,0,46,0.0,0.0,0.0
+545,Starting to label next square,0,6,0.0,0.0,0.0
+546,Placing labeled cardboard square,0,2,0.0,0.0,0.0
+547,Labeling cardboard piece,0,13,0.0,0.0,0.0
+548,Move cardboard piece,0,2,0.0,0.0,0.0
+549,Reach for next piece,0,1,0.0,0.0,0.0
+550,Marking cardboard with pen,0,2,0.0,0.0,0.0
+551,Repositioning ruler and cardboard,0,1,0.0,0.0,0.0
+552,Folding cardboard,0,1,0.0,0.0,0.0
+553,Place cardboard piece on stack,0,32,0.0,0.0,0.0
+554,Arrange buttons on the table,0,11,0.0,0.0,0.0
+555,Arrange buttons,33,18,1.0,0.5454545454545454,0.7058823529411764
+556,Sorting buttons,0,3,0.0,0.0,0.0
+557,Sort orange buttons,0,85,0.0,0.0,0.0
+558,Sort orange button,0,14,0.0,0.0,0.0
+559,Move hand over button pile,0,1,0.0,0.0,0.0
+560,Move orange buttons,0,17,0.0,0.0,0.0
+561,Arrange orange buttons,0,83,0.0,0.0,0.0
+562,Pick up stapler,0,9,0.0,0.0,0.0
+563,Drawing grid line with ruler,0,0,0.0,0.0,0.0
+564,Drawing grid line with pen and ruler,0,0,0.0,0.0,0.0
+565,Draw grid line with pen,0,2,0.0,0.0,0.0
+566,Pick up cardboard,0,2,0.0,0.0,0.0
+567,Draw grid line,0,0,0.0,0.0,0.0
+568,Drawing grid line,0,0,0.0,0.0,0.0
+569,Manipulate paper star,0,16,0.0,0.0,0.0
+570,Fold paper star,0,18,0.0,0.0,0.0
+571,Reach for beads,0,49,0.0,0.0,0.0
+572,Sort purple beads,0,0,0.0,0.0,0.0
+573,Write on paper,13,0,0.0,0.0,0.0
+574,Gathering star beads,0,1,0.0,0.0,0.0
+575,Sort beads by hand,0,8,0.0,0.0,0.0
+576,Pick up can,3,0,0.0,0.0,0.0
+577,Hold tray of canned goods,0,0,0.0,0.0,0.0
+578,Position tray,0,0,0.0,0.0,0.0
+579,Sort canned goods in tray,0,0,0.0,0.0,0.0
+580,Carry crate of cans,0,0,0.0,0.0,0.0
+581,Move can towards shelf,0,0,0.0,0.0,0.0
+582,Wipe item,0,0,0.0,0.0,0.0
+583,Place item back,0,0,0.0,0.0,0.0
+584,Wipe retail item,0,0,0.0,0.0,0.0
+585,Reach for retail item,0,0,0.0,0.0,0.0
+586,Grasp retail item,0,4,0.0,0.0,0.0
+587,Adjust retail items on shelf,0,0,0.0,0.0,0.0
+588,Align and place retail item,0,0,0.0,0.0,0.0
+589,Arrange items on shelf,0,0,0.0,0.0,0.0
+590,Pick up pink water bottle,0,3,0.0,0.0,0.0
+591,Place down pink water bottle,0,2,0.0,0.0,0.0
+592,Place star in row,0,0,0.0,0.0,0.0
+593,Reach for star,0,4,0.0,0.0,0.0
+594,Retrieve star,0,1,0.0,0.0,0.0
+595,Pick up star,0,1,0.0,0.0,0.0
+596,Hold recording sheet and pen,0,0,0.0,0.0,0.0
+597,Record star count,0,0,0.0,0.0,0.0
+598,Hold pen and paper,0,0,0.0,0.0,0.0
+599,Observe paper and count objects,0,0,0.0,0.0,0.0
+600,Write count on paper,17,139,0.0,0.0,0.0
+601,Place pen on table,0,0,0.0,0.0,0.0
+602,View content on smartphone,0,1,0.0,0.0,0.0
+603,Resume writing on paper,0,14,0.0,0.0,0.0
+604,Pick up paper star,0,1,0.0,0.0,0.0
+605,Place paper star in row,0,0,0.0,0.0,0.0
+606,Manipulate star,0,0,0.0,0.0,0.0
+607,Arrange paper stars,0,0,0.0,0.0,0.0
+608,Cut cardboard grid,0,0,0.0,0.0,0.0
+609,Pick up small item,0,0,0.0,0.0,0.0
+610,Walking to sink,0,0,0.0,0.0,0.0
+611,Washing hands,0,0,0.0,0.0,0.0
+612,Finish washing hands,0,0,0.0,0.0,0.0
+613,Pick up paper towel,0,0,0.0,0.0,0.0
+614,Dry hands,0,0,0.0,0.0,0.0
+615,Begin folding paper strip,0,0,0.0,0.0,0.0
+616,Fold paper strip into a star,0,8,0.0,0.0,0.0
+617,Prepare paper strip,0,0,0.0,0.0,0.0
+618,Continue folding paper strip,0,19,0.0,0.0,0.0
+619,Fold lucky star,0,0,0.0,0.0,0.0
+620,Manipulate folded paper star,0,1,0.0,0.0,0.0
+621,Grasp paper strip,0,0,0.0,0.0,0.0
+622,Sort colored tiles,0,0,0.0,0.0,0.0
+623,Pick up colored tile,0,0,0.0,0.0,0.0
+624,Place colored tile,0,0,0.0,0.0,0.0
+625,Sort tiles,0,0,0.0,0.0,0.0
+626,Sort tiles by color,0,0,0.0,0.0,0.0
+627,Write on notepad,0,49,0.0,0.0,0.0
+628,Writing on notepad,0,18,0.0,0.0,0.0
+629,Reaching for beads,0,2,0.0,0.0,0.0
+630,Cut section from newspaper,0,0,0.0,0.0,0.0
+631,Tear newspaper,0,0,0.0,0.0,0.0
+632,Hold newspaper,0,0,0.0,0.0,0.0
+633,Hold and align newspaper,0,0,0.0,0.0,0.0
+634,Fold newspaper,0,0,0.0,0.0,0.0
+635,Reposition newspaper,0,0,0.0,0.0,0.0
+636,Cut along the edge of the newspaper,0,0,0.0,0.0,0.0
+637,Cut along the newspaper edge,0,0,0.0,0.0,0.0
+638,Browsing mobile phone,0,0,0.0,0.0,0.0
+639,Browse mobile phone,0,0,0.0,0.0,0.0
+640,Cut newspaper with scissors,0,0,0.0,0.0,0.0
+641,Sort blue star-shaped pieces,0,3,0.0,0.0,0.0
+642,Sort small plastic pieces,0,0,0.0,0.0,0.0
+643,Reach for more pieces,0,0,0.0,0.0,0.0
+644,Sort plastic pieces,0,0,0.0,0.0,0.0
+645,Move pieces into box,0,0,0.0,0.0,0.0
+646,Gather pieces into box,0,0,0.0,0.0,0.0
+647,Typing on phone,0,0,0.0,0.0,0.0
+648,Scrolling and viewing content on phone,0,0,0.0,0.0,0.0
+649,Pick up item from shelf,0,0,0.0,0.0,0.0
+650,Pick up charging cable,0,0,0.0,0.0,0.0
+651,Pick up electronic item,0,0,0.0,0.0,0.0
+652,Wipe electronic item,0,1,0.0,0.0,0.0
+653,Place item in bag,0,1,0.0,0.0,0.0
+654,Inspect smartphone box,0,2,0.0,0.0,0.0
+655,Hold smartphone box,0,0,0.0,0.0,0.0
+656,Examine product,0,0,0.0,0.0,0.0
+657,Pick up another canned item,0,6,0.0,0.0,0.0
+658,Carry plastic container,0,5,0.0,0.0,0.0
+659,Reach for another container,0,7,0.0,0.0,0.0
+660,Release container,0,15,0.0,0.0,0.0
+661,Pick up storage container,0,7,0.0,0.0,0.0
+662,Move container toward shelf,0,8,0.0,0.0,0.0
+663,Position container on shelf,0,8,0.0,0.0,0.0
+664,Remove lid from container,0,7,0.0,0.0,0.0
+665,Pick up canned goods,0,7,0.0,0.0,0.0
+666,Place canned goods in container,0,5,0.0,0.0,0.0
+667,Pick up next product from bin,0,4,0.0,0.0,0.0
+668,Move bin,0,32,0.0,0.0,0.0
+669,Walking along the aisle,0,0,0.0,0.0,0.0
+670,Move plastic storage bin,0,0,0.0,0.0,0.0
+671,Place canned food in bin,0,0,0.0,0.0,0.0
+672,Hold container of canned food,0,0,0.0,0.0,0.0
+673,Move towards aisle,0,0,0.0,0.0,0.0
+674,Approach restocking supplies,0,0,0.0,0.0,0.0
+675,Pick up plastic container,0,0,0.0,0.0,0.0
+676,Move along the shelves,0,0,0.0,0.0,0.0
+677,Forming quilled paper shape,0,0,0.0,0.0,0.0
+678,Manipulate quilled paper shape,0,0,0.0,0.0,0.0
+679,Place quilled paper shape,0,0,0.0,0.0,0.0
+680,Retrieve paper strip,0,0,0.0,0.0,0.0
+681,Select paper strip,0,0,0.0,0.0,0.0
+682,Transition to standing position,0,0,0.0,0.0,0.0
+683,Observe paper quilling station,0,0,0.0,0.0,0.0
+684,Sort quilled paper pieces,0,1,0.0,0.0,0.0
+685,Walk towards storage area,0,2,0.0,0.0,0.0
+686,Hold device and cable,0,0,0.0,0.0,0.0
+687,Move piece to pile,0,0,0.0,0.0,0.0
+688,Manipulate quilled paper,0,1,0.0,0.0,0.0
+689,Pick up and sort cardboard,0,0,0.0,0.0,0.0
+690,Sort and arrange cardboard pieces,0,0,0.0,0.0,0.0
+691,Move camera over surface,0,0,0.0,0.0,0.0
+692,Observe sorting progress,0,5,0.0,0.0,0.0
+693,Reach for cardboard piece,0,1,0.0,0.0,0.0
+694,Lock phone,0,0,0.0,0.0,0.0
+695,Sort and stack cardboard pieces,0,0,0.0,0.0,0.0
+696,Mark list with pen,0,0,0.0,0.0,0.0
+697,Adjust bead piles,0,0,0.0,0.0,0.0
+698,Sort blue beads,0,2,0.0,0.0,0.0
+699,Place down pen,0,1,0.0,0.0,0.0
+700,Move away from desk,0,0,0.0,0.0,0.0
+701,Walking through the office,0,3,0.0,0.0,0.0
+702,Resume sorting blue beads,0,0,0.0,0.0,0.0
+703,Fold cardboard shape,0,4,0.0,0.0,0.0
+704,Reach for cardboard box,0,9,0.0,0.0,0.0
+705,Reach for object,0,5,0.0,0.0,0.0
+706,Release cardboard shape,0,2,0.0,0.0,0.0
+707,Reposition hands,0,0,0.0,0.0,0.0
+708,Rolling paper strip,0,0,0.0,0.0,0.0
+709,Finishing coil,0,2,0.0,0.0,0.0
+710,Start folding paper strip,0,0,0.0,0.0,0.0
+711,Folding paper strip,0,4,0.0,0.0,0.0
+712,Positioning paper strip,0,5,0.0,0.0,0.0
+713,Manipulate quilling paper,0,0,0.0,0.0,0.0
+714,Walk towards workspace,0,0,0.0,0.0,0.0
+715,Interaction with coworker,0,0,0.0,0.0,0.0
+716,Walk through workspace,0,0,0.0,0.0,0.0
+717,Manipulate small object,0,0,0.0,0.0,0.0
+718,Manipulate paper quilling piece,0,3,0.0,0.0,0.0
+719,Hold quilled paper piece,0,4,0.0,0.0,0.0
+720,Pull paper strip,0,10,0.0,0.0,0.0
+721,Hold and align paper strip,0,1,0.0,0.0,0.0
+722,Hold and rotate paper strip,0,1,0.0,0.0,0.0
+723,Marking cardboard piece,30,0,0.0,0.0,0.0
+724,Hold and mark cardboard piece,0,0,0.0,0.0,0.0
+725,Organize cardboard pieces,15,2,0.0,0.0,0.0
+726,Walking towards workstation,0,0,0.0,0.0,0.0
+727,Move to desk,0,0,0.0,0.0,0.0
+728,Sort small objects,0,0,0.0,0.0,0.0
+729,Gathering items,0,0,0.0,0.0,0.0
+730,Place items on table,0,0,0.0,0.0,0.0
+731,Gathering colored beads,0,0,0.0,0.0,0.0
+732,Arrange beads by color,0,0,0.0,0.0,0.0
+733,Sort star-shaped objects by color,0,0,0.0,0.0,0.0
+734,Sort star-shaped objects,0,0,0.0,0.0,0.0
+735,Sort yellow star-shaped objects,0,0,0.0,0.0,0.0
+736,Sort purple star-shaped objects,0,0,0.0,0.0,0.0
+737,View phone screen,0,0,0.0,0.0,0.0
+738,Viewing phone screen,0,0,0.0,0.0,0.0
+739,Initiate star folding,0,0,0.0,0.0,0.0
+740,Reach for next canned product,0,0,0.0,0.0,0.0
+741,Place jar in box,0,11,0.0,0.0,0.0
+742,Place pickle jar in box,0,6,0.0,0.0,0.0
+743,Grasp product from shelf,0,0,0.0,0.0,0.0
+744,Place red button,0,0,0.0,0.0,0.0
+745,Move and place black buttons,0,9,0.0,0.0,0.0
+746,Arrange red buttons,0,1,0.0,0.0,0.0
+747,Adjust red button position,0,0,0.0,0.0,0.0
+748,Withdraw hand from buttons,0,1,0.0,0.0,0.0
+749,Arrive at a different workstation,0,0,0.0,0.0,0.0
+750,Move vacuum cleaner hose,0,2,0.0,0.0,0.0
+751,Place smartphone on cardboard,0,6,0.0,0.0,0.0
+752,Reach into bag,0,0,0.0,0.0,0.0
+753,Organize products,0,1,0.0,0.0,0.0
+754,Close cardboard box,0,3,0.0,0.0,0.0
+755,Pick up item,0,0,0.0,0.0,0.0
+756,Stand up and walk away,0,6,0.0,0.0,0.0
+757,Interact with colleagues,0,0,0.0,0.0,0.0
+758,Moving hand towards cardboard stack,0,3,0.0,0.0,0.0
+759,Put down water bottle,0,0,0.0,0.0,0.0
+760,Placing piece on stack,0,0,0.0,0.0,0.0
+761,Reach for and pick up smartphone,0,2,0.0,0.0,0.0
+762,Move cardboard to pile,0,0,0.0,0.0,0.0
+763,Fold cardboard sheet,0,0,0.0,0.0,0.0
+764,Reach for shelving divider,0,2,0.0,0.0,0.0
+765,Rearrange shelf item,0,2,0.0,0.0,0.0
+766,Arrange paper strips,0,7,0.0,0.0,0.0
+767,Place down strip,0,10,0.0,0.0,0.0
+768,Move puzzle piece,0,2,0.0,0.0,0.0
+769,Cap marker,0,1,0.0,0.0,0.0
+770,Combine bead piles,0,0,0.0,0.0,0.0
+771,Draw lines with pen and ruler,0,0,0.0,0.0,0.0
+772,Put down phone,0,6,0.0,0.0,0.0
+773,Pick up pasta box,0,1,0.0,0.0,0.0
+774,Place gift box into bin,0,0,0.0,0.0,0.0
+775,Remove plastic container from storage box,0,3,0.0,0.0,0.0
+776,Hold ruler,0,0,0.0,0.0,0.0
+777,Move pen away,0,3,0.0,0.0,0.0
+778,Place crate on floor,0,0,0.0,0.0,0.0
+779,Place smartphone on table,0,3,0.0,0.0,0.0
+780,Discard paper towel,0,0,0.0,0.0,0.0
+781,Release paper star,0,2,0.0,0.0,0.0
+782,Place phone on table,0,1,0.0,0.0,0.0
+783,Scrolling or navigating on phone,0,1,0.0,0.0,0.0
+784,Hold electronic item,0,0,0.0,0.0,0.0
+785,Inspect electronic item,0,0,0.0,0.0,0.0
+786,Move pineapple chips,0,0,0.0,0.0,0.0
+787,Mark paper list,0,0,0.0,0.0,0.0
+788,Placing phone down,0,4,0.0,0.0,0.0
+789,Pick up nut bar box,0,0,0.0,0.0,0.0
+790,Pick up plastic bin,0,0,0.0,0.0,0.0
+791,Pick up pickle jar,0,4,0.0,0.0,0.0
+792,Pick up product from shelf,0,2,0.0,0.0,0.0
+793,Place jar into shelf box,0,7,0.0,0.0,0.0
+794,Wipe grocery shelf,0,0,0.0,0.0,0.0
+795,Rearrange buttons,0,1,0.0,0.0,0.0
+796,Release button,0,0,0.0,0.0,0.0
+797,Pick up orange button,0,1,0.0,0.0,0.0
+798,Arrange small buttons,0,7,0.0,0.0,0.0
+799,Align buttons,0,1,0.0,0.0,0.0
+800,Look around the table,0,0,0.0,0.0,0.0
+801,Align red buttons,0,0,0.0,0.0,0.0
+802,Reach for black button,0,6,0.0,0.0,0.0
+803,Reach for buttons,0,8,0.0,0.0,0.0
+804,Place and align button,0,0,0.0,0.0,0.0
+805,Move hand,0,0,0.0,0.0,0.0
+806,Move button to line,0,0,0.0,0.0,0.0
+807,Reach for utility knife,0,5,0.0,0.0,0.0
+808,Place down paper pieces,0,0,0.0,0.0,0.0
+809,Switch to scissors,0,0,0.0,0.0,0.0
+810,Place phone on shelf,0,1,0.0,0.0,0.0
+811,Inspect product lid,0,7,0.0,0.0,0.0
+812,Sweep floor debris,0,1,0.0,0.0,0.0
+813,Adjust grip on container,0,0,0.0,0.0,0.0
+814,Manipulate paper piece,0,1,0.0,0.0,0.0
+815,Hold quilled paper coil,0,5,0.0,0.0,0.0
+816,Place scissors aside,0,0,0.0,0.0,0.0
+817,Finish placing cardboard cutouts,0,4,0.0,0.0,0.0
+818,Fold cut cardboard,0,7,0.0,0.0,0.0
+819,Look away,0,0,0.0,0.0,0.0
+820,Pick up cut cardboard piece,0,1,0.0,0.0,0.0
+821,Reposition scissors,0,2,0.0,0.0,0.0
+822,Hold cardboard piece,7,4,0.0,0.0,0.0
+823,Picking up stock,0,0,0.0,0.0,0.0
+824,Carry container,0,3,0.0,0.0,0.0
+825,Positioning cardboard on workspace,0,1,0.0,0.0,0.0
+826,Stop sorting stars,0,0,0.0,0.0,0.0
+827,Place knife down,0,0,0.0,0.0,0.0
+828,Search for puzzle piece,20,3,0.0,0.0,0.0
+829,Lift pen and shift ruler,0,0,0.0,0.0,0.0
+830,Moving ruler,0,0,0.0,0.0,0.0
+831,Hold beads,19,0,0.0,0.0,0.0
+832,Adjusting fabric position,0,0,0.0,0.0,0.0
+833,Pick up new cardboard piece,24,0,0.0,0.0,0.0
+834,Gather cardboard pieces,0,0,0.0,0.0,0.0
+835,Hold electronic accessory,0,0,0.0,0.0,0.0
+836,Pick up electronic accessory,0,0,0.0,0.0,0.0
+837,Place accessory box,0,0,0.0,0.0,0.0
+838,Release product on shelf,0,0,0.0,0.0,0.0
+839,Pick up new product from box,0,0,0.0,0.0,0.0
+840,Pick up shopping bag,0,0,0.0,0.0,0.0
+841,Move to shelf,3,0,0.0,0.0,0.0
+842,Grasp snack package,0,0,0.0,0.0,0.0
+843,Place snack in box,0,7,0.0,0.0,0.0
+844,Place snack packages on shelf,0,7,0.0,0.0,0.0
+845,Reach for snack package,0,0,0.0,0.0,0.0
+846,Reach for item,0,0,0.0,0.0,0.0
+847,Organize item on shelf,0,0,0.0,0.0,0.0
+848,Place pen on cardboard,0,0,0.0,0.0,0.0
+849,Adjust cardboard divider,0,2,0.0,0.0,0.0
+850,Place finished star on table,0,4,0.0,0.0,0.0
+851,Inspect shelf,0,2,0.0,0.0,0.0
+852,Pick up snack packs,0,4,0.0,0.0,0.0
+853,Move to shelf base,0,3,0.0,0.0,0.0
+854,Place gift box on shelf,0,0,0.0,0.0,0.0
+855,Place snack pouch on shelf,0,0,0.0,0.0,0.0
+856,Sort Mahjong tiles,0,1,0.0,0.0,0.0
+857,Pick up charging case,0,8,0.0,0.0,0.0
+858,Place ruler on cardboard,0,0,0.0,0.0,0.0
+859,Reposition tools,0,0,0.0,0.0,0.0
+860,Position scissors for next cut,0,0,0.0,0.0,0.0
+861,Tapping on smartphone screen,0,0,0.0,0.0,0.0
+862,Positioning ruler on cardboard,0,5,0.0,0.0,0.0
+863,Placing labeled square,0,3,0.0,0.0,0.0
+864,Switching marker,0,4,0.0,0.0,0.0
+865,Placing pen on table,0,3,0.0,0.0,0.0
+866,Manipulate cardboard sheet,0,0,0.0,0.0,0.0
+867,Interact with smartphone,21,2,0.0,0.0,0.0
+868,Pick up retail item,0,0,0.0,0.0,0.0
+869,Adjust retail item position,0,0,0.0,0.0,0.0
+870,Observe surroundings,0,4,0.0,0.0,0.0
+871,Manipulate paper stars,0,1,0.0,0.0,0.0
+872,Pick up power bank,0,0,0.0,0.0,0.0
+873,Rub hands together,0,1,0.0,0.0,0.0
+874,Place star on table,0,2,0.0,0.0,0.0
+875,Gather pieces,0,0,0.0,0.0,0.0
+876,Select another item,0,3,0.0,0.0,0.0
+877,Place container on floor,0,3,0.0,0.0,0.0
+878,Place storage container on floor,0,3,0.0,0.0,0.0
+879,Reorganize bin contents,0,2,0.0,0.0,0.0
+880,Observe stocking,0,1,0.0,0.0,0.0
+881,Manipulate quilled paper strips,0,0,0.0,0.0,0.0
+882,Move blue beads,0,6,0.0,0.0,0.0
+883,Place controller on table,0,2,0.0,0.0,0.0
+884,Selecting new paper strip,0,3,0.0,0.0,0.0
+885,Grasp electronic object,0,1,0.0,0.0,0.0
+886,Reach for paper strip,0,5,0.0,0.0,0.0
+887,Reach for canned food,0,0,0.0,0.0,0.0
+888,Hold blue product box,0,0,0.0,0.0,0.0
+889,Inspect product,0,0,0.0,0.0,0.0
+890,Clean shelf,0,0,0.0,0.0,0.0
+891,Walk towards shelf,0,0,0.0,0.0,0.0
+892,Select product from box,0,0,0.0,0.0,0.0
+893,Wipe ketchup bottle,0,0,0.0,0.0,0.0
+894,Place ketchup bottle on shelf,0,0,0.0,0.0,0.0
+895,Draw line with marker,0,0,0.0,0.0,0.0
+896,Draw straight line,0,0,0.0,0.0,0.0
+897,Mark straight line,0,0,0.0,0.0,0.0
+898,Pick up small cardboard piece,0,0,0.0,0.0,0.0
+899,Walk through office,0,0,0.0,0.0,0.0
+900,Cut cardboard along line,0,0,0.0,0.0,0.0
+901,Reposition hands and ruler,0,0,0.0,0.0,0.0
+902,Align ruler with crease,0,0,0.0,0.0,0.0
+903,Press fold,0,0,0.0,0.0,0.0
+904,Cut cardboard strip with utility knife,0,0,0.0,0.0,0.0
+905,Pick up dustpan,17,0,0.0,0.0,0.0
+906,Hold container lid,25,0,0.0,0.0,0.0
+907,Move towards the stove,9,0,0.0,0.0,0.0
+908,Open stove pot lid,20,0,0.0,0.0,0.0
+909,Closing the door,8,0,0.0,0.0,0.0
+910,Picking up bottle,11,0,0.0,0.0,0.0
+911,Wipe kitchen counter,16,0,0.0,0.0,0.0
+912,Move towards kitchen area,15,0,0.0,0.0,0.0
+913,Place cloth on floor,6,0,0.0,0.0,0.0
+914,Reach for cleaning supplies,18,0,0.0,0.0,0.0
+915,Remove cleaning bottle,11,0,0.0,0.0,0.0
+916,Washing hands in sink,10,0,0.0,0.0,0.0
+917,Grasping cleaning cloth,7,0,0.0,0.0,0.0
+918,Wiping countertop,11,0,0.0,0.0,0.0
+919,Lift pot lid,9,0,0.0,0.0,0.0
+920,Stir contents,8,0,0.0,0.0,0.0
+921,Place lid back,9,0,0.0,0.0,0.0
+922,Adjust pot position,6,0,0.0,0.0,0.0
+923,Move pot,7,0,0.0,0.0,0.0
+924,Place towel,16,0,0.0,0.0,0.0
+925,Start cutting,7,0,0.0,0.0,0.0
+926,Cut along the marked line,51,0,0.0,0.0,0.0
+927,Pick up item from bin,0,0,0.0,0.0,0.0
+928,Hold item,0,0,0.0,0.0,0.0
+929,Check smart watch,0,0,0.0,0.0,0.0
+930,Pick up jar,0,0,0.0,0.0,0.0
+931,Pick up sauce bottle,0,0,0.0,0.0,0.0
+932,Place sauce bottle on shelf,0,0,0.0,0.0,0.0
+933,Hold empty container,0,0,0.0,0.0,0.0
+934,Assess shelf arrangement,0,0,0.0,0.0,0.0
+935,Pick up bottle,0,0,0.0,0.0,0.0
+936,Release foam strip,0,0,0.0,0.0,0.0
+937,Observe craft layout,0,0,0.0,0.0,0.0
+938,Reach for foam strips,0,0,0.0,0.0,0.0
+939,Adjust foam strip,0,0,0.0,0.0,0.0
+940,Align foam strip,0,0,0.0,0.0,0.0
+941,Attach foam strip,0,0,0.0,0.0,0.0
+942,Curve foam strip into loop,0,0,0.0,0.0,0.0
+943,Press ends of foam strip together,0,0,0.0,0.0,0.0
+944,Position yellow foam piece on strip,0,0,0.0,0.0,0.0
+945,Press foam strip,0,0,0.0,0.0,0.0
+946,Fold foam piece,0,0,0.0,0.0,0.0
+947,Pinch foam strips,0,0,0.0,0.0,0.0
+948,Pull blue foam strip,0,0,0.0,0.0,0.0
+949,Tear blue foam strip,0,0,0.0,0.0,0.0
+950,Pick up blue foam piece,0,0,0.0,0.0,0.0
+951,Tear blue foam piece,0,0,0.0,0.0,0.0
+952,Tear off blue foam piece,0,0,0.0,0.0,0.0
+953,Peel foam strip,0,0,0.0,0.0,0.0
+954,Move small blue foam piece towards the strip,0,0,0.0,0.0,0.0
+955,Align blue strip,0,0,0.0,0.0,0.0
+956,Press blue strip,0,0,0.0,0.0,0.0
+957,Position blue strip,0,0,0.0,0.0,0.0
+958,Lift blue strip,0,0,0.0,0.0,0.0
+959,Hold blue strip,0,0,0.0,0.0,0.0
+960,Peel blue strip,0,0,0.0,0.0,0.0
+961,Align paper strip,0,0,0.0,0.0,0.0
+962,Interlock paper strips,0,0,0.0,0.0,0.0
+963,Turn away from table,0,0,0.0,0.0,0.0
+964,Touch phone and paper strip,0,0,0.0,0.0,0.0
+965,Attach material to paper strip,0,0,0.0,0.0,0.0
+966,Pick up tool,0,0,0.0,0.0,0.0
+967,Walk through the room,0,0,0.0,0.0,0.0
+968,Walk down hallway,0,0,0.0,0.0,0.0
+969,Reach for door handle,0,0,0.0,0.0,0.0
+970,Grasp door handle,0,0,0.0,0.0,0.0
+971,Walk to table,0,0,0.0,0.0,0.0
+972,Pick up supplies from box,0,0,0.0,0.0,0.0
+973,Approach work table,0,0,0.0,0.0,0.0
+974,Touch colleague's back,0,0,0.0,0.0,0.0
+975,Position the chair,0,0,0.0,0.0,0.0
+976,Observe and walk through store,15,0,0.0,0.0,0.0
+977,Inspect shelf condition,27,0,0.0,0.0,0.0
+978,Approach boxes,12,0,0.0,0.0,0.0
+979,Reach for wire hangers,13,0,0.0,0.0,0.0
+980,Extract wire hangers from box,30,0,0.0,0.0,0.0
+981,Bundle display hooks,22,0,0.0,0.0,0.0
+982,Release hook,14,0,0.0,0.0,0.0
+983,Move through aisle,10,0,0.0,0.0,0.0
+984,Pick up items from the shopping bag,23,0,0.0,0.0,0.0
+985,Place items on the shelf,6,0,0.0,0.0,0.0
+986,Release cardboard piece and gesture,16,0,0.0,0.0,0.0
+987,Move marker and adjust hand,8,0,0.0,0.0,0.0
+988,Identify next cardboard piece,21,0,0.0,0.0,0.0
+989,Observe and pause,11,0,0.0,0.0,0.0
+990,Resume observation,4,0,0.0,0.0,0.0
+991,Reach for and examine canned goods,0,0,0.0,0.0,0.0
+992,Examine canned goods,0,0,0.0,0.0,0.0
+993,Select and pick up a canned item,0,0,0.0,0.0,0.0
+994,Place item back on shelf,0,0,0.0,0.0,0.0
+995,Inspect Dior gift box,0,0,0.0,0.0,0.0
+996,Move along the shelf,0,0,0.0,0.0,0.0
+997,Select a bottle,0,0,0.0,0.0,0.0
+998,Place bottle back on shelf,0,0,0.0,0.0,0.0
+999,Pick up another bottle,0,0,0.0,0.0,0.0
+1000,Release bottle,0,0,0.0,0.0,0.0
+1001,Inspect bottle,0,0,0.0,0.0,0.0
+1002,Inspect almond package,0,0,0.0,0.0,0.0
+1003,Scan supermarket shelves,0,0,0.0,0.0,0.0
+1004,Move along the supermarket aisle,0,0,0.0,0.0,0.0
+1005,Reach for canned goods,0,0,0.0,0.0,0.0
+1006,Touch canned goods,0,0,0.0,0.0,0.0
+1007,Manipulate cardboard shape,0,0,0.0,0.0,0.0
+1008,Hold small cardboard pieces,0,0,0.0,0.0,0.0
+1009,Prepare to place cardboard,0,0,0.0,0.0,0.0
+1010,Reach for next can,18,0,0.0,0.0,0.0
+1011,Hold canned food,24,0,0.0,0.0,0.0
+1012,Retrieve next canned food item,17,0,0.0,0.0,0.0
+1013,Align canned food on shelf,9,0,0.0,0.0,0.0
+1014,Retrieve canned food from box,12,0,0.0,0.0,0.0
+1015,Place another canned food on shelf,11,0,0.0,0.0,0.0
+1016,Adjust canned food on shelf,9,0,0.0,0.0,0.0
+1017,Move hand away from shelf,8,0,0.0,0.0,0.0
+1018,Hold earbud case,21,0,0.0,0.0,0.0
+1019,sort craft materials,36,0,0.0,0.0,0.0
+1020,Manipulate craft piece,38,0,0.0,0.0,0.0
+1021,Manipulate craft paper strips,33,0,0.0,0.0,0.0
+1022,Operate smartphone,40,0,0.0,0.0,0.0
+1023,Release smartphone,7,0,0.0,0.0,0.0
+1024,Sort small craft pieces,39,0,0.0,0.0,0.0
+1025,Hold product package,0,0,0.0,0.0,0.0
+1026,Check phone,0,0,0.0,0.0,0.0
+1027,Hold charging cable,0,0,0.0,0.0,0.0
+1028,Hold items in hand,0,0,0.0,0.0,0.0
+1029,Hold and examine item,0,0,0.0,0.0,0.0
+1030,Remove item from bag,0,0,0.0,0.0,0.0
+1031,Pick up pack from shelf,0,0,0.0,0.0,0.0
+1032,fold purple ribbon,0,0,0.0,0.0,0.0
+1033,Fold ribbon,0,0,0.0,0.0,0.0
+1034,Hold small piece of ribbon,0,0,0.0,0.0,0.0
+1035,Position ribbon piece,0,0,0.0,0.0,0.0
+1036,Manipulate ribbon piece,0,0,0.0,0.0,0.0
+1037,Place ribbon onto project,0,0,0.0,0.0,0.0
+1038,Fold and manipulate ribbon,0,0,0.0,0.0,0.0
+1039,Manipulate ribbon knot,0,0,0.0,0.0,0.0
+1040,Secure ribbon with needle,0,0,0.0,0.0,0.0
+1041,Open paper lantern,29,0,0.0,0.0,0.0
+1042,Fold paper lantern,9,0,0.0,0.0,0.0
+1043,Grasp lantern,15,0,0.0,0.0,0.0
+1044,Grasp lantern component,15,0,0.0,0.0,0.0
+1045,Align paper lantern edges,29,0,0.0,0.0,0.0
+1046,Release lantern,13,0,0.0,0.0,0.0
+1047,Pick up packaged paper lantern component,12,0,0.0,0.0,0.0
+1048,Handle paper lantern component,19,0,0.0,0.0,0.0
+1049,Open folded paper lantern,21,0,0.0,0.0,0.0
+1050,Hold paper lantern,19,0,0.0,0.0,0.0
+1051,Apply adhesive tape to lantern,14,0,0.0,0.0,0.0
+1052,Remove paper lantern part from packaging,16,0,0.0,0.0,0.0
+1053,Remove plastic packaging,8,0,0.0,0.0,0.0
+1054,Open paper lantern component,24,0,0.0,0.0,0.0
+1055,Expand paper lantern,22,0,0.0,0.0,0.0
+1056,Align edges of paper lantern,6,0,0.0,0.0,0.0
+1057,Mark cardboard with ruler,0,0,0.0,0.0,0.0
+1058,Cut along the line,0,0,0.0,0.0,0.0
+1059,Release cardboard,0,0,0.0,0.0,0.0
+1060,Reposition utility knife,0,0,0.0,0.0,0.0
+1061,Tear off cardboard segment,0,0,0.0,0.0,0.0
+1062,Browsing smartphone content,0,0,0.0,0.0,0.0
+1063,Manipulate small component,0,0,0.0,0.0,0.0
+1064,Manipulate component on strip,0,0,0.0,0.0,0.0
+1065,Place strip on table,0,0,0.0,0.0,0.0
+1066,Manipulate component,0,0,0.0,0.0,0.0
+1067,Reach for craft items,18,0,0.0,0.0,0.0
+1068,Place hand on table,33,0,0.0,0.0,0.0
+1069,Browse smartphone screen,33,0,0.0,0.0,0.0
+1070,Scroll smartphone screen,31,0,0.0,0.0,0.0
+1071,Put down smartphone,26,0,0.0,0.0,0.0
+1072,Place smartphone down,24,0,0.0,0.0,0.0
+1073,Record count on notepad,0,0,0.0,0.0,0.0
+1074,Count and record paper stars,0,0,0.0,0.0,0.0
+1075,Record star count on paper,0,0,0.0,0.0,0.0
+1076,Connect cable to device,0,0,0.0,0.0,0.0
+1077,Place device on lap,0,0,0.0,0.0,0.0
+1078,Count and arrange paper stars,0,0,0.0,0.0,0.0
+1079,Count paper stars,0,0,0.0,0.0,0.0
+1080,Move hand to paper stars,0,0,0.0,0.0,0.0
+1081,Resume counting stars,0,0,0.0,0.0,0.0
+1082,Reviewing count record,0,0,0.0,0.0,0.0
+1083,Write on paper record,0,0,0.0,0.0,0.0
+1084,Update paper record,0,0,0.0,0.0,0.0
+1085,Adjust cardboard,0,0,0.0,0.0,0.0
+1086,Set down scissors and pick up power bank,0,0,0.0,0.0,0.0
+1087,Reposition cardboard for cutting,0,0,0.0,0.0,0.0
+1088,Arrange cardboard pieces,0,0,0.0,0.0,0.0
+1089,Mark cardboard strip with pen,0,0,0.0,0.0,0.0
+1090,Pick up puzzle piece,18,0,0.0,0.0,0.0
+1091,Place piece into puzzle,25,0,0.0,0.0,0.0
+1092,Manipulate puzzle piece,38,0,0.0,0.0,0.0
+1093,Observe puzzle progress,32,0,0.0,0.0,0.0
+1094,Reach for puzzle piece,16,0,0.0,0.0,0.0
+1095,Attempt to fit puzzle piece,31,0,0.0,0.0,0.0
+1096,Sort puzzle pieces,34,0,0.0,0.0,0.0
+1097,Walking across the room,17,0,0.0,0.0,0.0
+1098,Approaching the table,9,0,0.0,0.0,0.0
+1099,Preparing to craft,10,0,0.0,0.0,0.0
+1100,Picking up crafting material,12,0,0.0,0.0,0.0
+1101,Manipulate material,16,0,0.0,0.0,0.0
+1102,Place material,13,0,0.0,0.0,0.0
+1103,Manipulate yellow strip,31,0,0.0,0.0,0.0
+1104,Manipulating paper strips,22,0,0.0,0.0,0.0
+1105,Manipulate bead,23,0,0.0,0.0,0.0
+1106,Manipulate beads,22,0,0.0,0.0,0.0
+1107,Hold and manipulate paper strip,31,0,0.0,0.0,0.0
+1108,Repositioning ruler,0,0,0.0,0.0,0.0
+1109,Place down ruler and pen,0,0,0.0,0.0,0.0
+1110,Walk through hallway,0,0,0.0,0.0,0.0
+1111,Fold cardboard edge,0,0,0.0,0.0,0.0
+1112,Pick up marker,0,0,0.0,0.0,0.0
+1113,Drop cardboard square into box,0,0,0.0,0.0,0.0
+1114,Retrieve hand to table,0,0,0.0,0.0,0.0
+1115,Pick up cardboard stack,0,0,0.0,0.0,0.0
+1116,Walk with cardboard,0,0,0.0,0.0,0.0
+1117,Deposit cardboard squares,0,0,0.0,0.0,0.0
+1118,Move away from collection box,0,0,0.0,0.0,0.0
+1119,Walking through office hallway,0,0,0.0,0.0,0.0
+1120,Grasp cardboard sheet,0,0,0.0,0.0,0.0
+1121,Cut cardboard sheet with scissors,0,0,0.0,0.0,0.0
+1122,Sort cut cardboard,0,0,0.0,0.0,0.0
+1123,Cut cardboard sheet,0,0,0.0,0.0,0.0
+1124,Place cardboard square,0,0,0.0,0.0,0.0
+1125,Sort buttons,25,0,0.0,0.0,0.0
+1126,Arrange buttons in a line,29,0,0.0,0.0,0.0
+1127,Sort and arrange buttons,32,0,0.0,0.0,0.0
+1128,Sort button,36,0,0.0,0.0,0.0
+1129,Sort and adjust button line,29,0,0.0,0.0,0.0
+1130,Sort and place buttons,31,0,0.0,0.0,0.0
+1131,Walking in the hallway,13,0,0.0,0.0,0.0
+1132,Approaching and pressing the door switch,22,0,0.0,0.0,0.0
+1133,Entering the VR training room,16,0,0.0,0.0,0.0
+1134,Greeting/acknowledging participants,33,0,0.0,0.0,0.0
+1135,Move through the training room,20,0,0.0,0.0,0.0
+1136,Manipulate plastic strips,34,0,0.0,0.0,0.0
+1137,Manipulate plastic strip,37,0,0.0,0.0,0.0
+1138,Hold and bend plastic strip,16,0,0.0,0.0,0.0
+1139,Bend and manipulate plastic strip,37,0,0.0,0.0,0.0
+1140,Fold plastic strip,57,0,0.0,0.0,0.0
+1141,Sort buttons by color,0,0,0.0,0.0,0.0
+1142,Sort button by color,0,0,0.0,0.0,0.0
+1143,Place button in group,0,0,0.0,0.0,0.0
+1144,Move away from table,0,0,0.0,0.0,0.0
+1145,Return to sorting,0,0,0.0,0.0,0.0
+1146,Manipulate paper decoration,41,0,0.0,0.0,0.0
+1147,Manipulate paper edge,35,0,0.0,0.0,0.0
+1148,Placing paper strip,44,0,0.0,0.0,0.0
+1149,Securing paper structure,37,0,0.0,0.0,0.0
+1150,Manipulate adhesive strip,44,0,0.0,0.0,0.0
+1151,Secure paper edges with adhesive,40,0,0.0,0.0,0.0
+1152,Record count,18,0,0.0,0.0,0.0
+1153,Sort beads and write count,18,0,0.0,0.0,0.0
+1154,Counting and organizing beads,19,0,0.0,0.0,0.0
+1155,Pick up star bead,6,0,0.0,0.0,0.0
+1156,Place and count bead,27,0,0.0,0.0,0.0
+1157,Arrange star beads,15,0,0.0,0.0,0.0
+1158,Counting star beads,23,0,0.0,0.0,0.0
+1159,Adjust paper,9,0,0.0,0.0,0.0
+1160,Gather star beads,13,0,0.0,0.0,0.0
+1161,Arrange star beads for counting,16,0,0.0,0.0,0.0
+1162,Sort and count beads,27,0,0.0,0.0,0.0
+1163,Rinse cloth in sink,4,0,0.0,0.0,0.0
+1164,Reposition hand,7,0,0.0,0.0,0.0
+1165,Touch foam strip,0,0,0.0,0.0,0.0
+1166,Assemble foam strips,0,0,0.0,0.0,0.0
+1167,Press foam piece to strip,0,0,0.0,0.0,0.0
+1168,Walk towards other aisles,4,0,0.0,0.0,0.0
+1169,Place marked piece down,14,0,0.0,0.0,0.0
+1170,Gesturing,2,0,0.0,0.0,0.0
+1171,Prepare to resume cutting,0,0,0.0,0.0,0.0
+1172,Reach for next canned food,3,0,0.0,0.0,0.0
+1173,Move hand away,5,0,0.0,0.0,0.0
+1174,Sort craft items,6,0,0.0,0.0,0.0
+1175,Retrieving more beads,5,0,0.0,0.0,0.0
+1176,Pick up yellow item,0,0,0.0,0.0,0.0
+1177,Prepare to place bottle on shelf,0,0,0.0,0.0,0.0
+1178,Move ruler and tools,0,0,0.0,0.0,0.0
+1179,Transition to cutting,0,0,0.0,0.0,0.0
+1180,Position utility knife on cardboard,0,0,0.0,0.0,0.0
+1181,Place smartphone on stand,3,0,0.0,0.0,0.0
+1182,Move dustpan to side,3,0,0.0,0.0,0.0
+1183,Walking towards door,3,0,0.0,0.0,0.0
+1184,Grasp cleaning bottle,3,0,0.0,0.0,0.0
+1185,Pick up next item from bin,0,0,0.0,0.0,0.0
+1186,Inspect and place item on shelf,0,0,0.0,0.0,0.0
+1187,Place blue foam piece,0,0,0.0,0.0,0.0
+1188,Hold foam pieces,0,0,0.0,0.0,0.0
+1189,Fold blue strip,0,0,0.0,0.0,0.0
+1190,Pick up craft material,0,0,0.0,0.0,0.0
+1191,Enter workspace,0,0,0.0,0.0,0.0
+1192,Enter the room,0,0,0.0,0.0,0.0
+1193,Pull chair,0,0,0.0,0.0,0.0
+1194,Observe colleague and workspace,3,0,0.0,0.0,0.0
+1195,Pick up Dior gift box,0,0,0.0,0.0,0.0
+1196,Place back Dior gift box,0,0,0.0,0.0,0.0
+1197,Pick up canned good,0,0,0.0,0.0,0.0
+1198,Open earbud case,3,0,0.0,0.0,0.0
+1199,Retrieve items from bag,0,0,0.0,0.0,0.0
+1200,Adjust lantern string,3,0,0.0,0.0,0.0
+1201,Adjust lantern shape,3,0,0.0,0.0,0.0
+1202,Pick up electronic device,0,0,0.0,0.0,0.0
+1203,Pick up small piece of material,3,0,0.0,0.0,0.0
+1204,Use phone while crafting,3,0,0.0,0.0,0.0
+1205,Approaching work table,0,0,0.0,0.0,0.0
+1206,Set down utility knife,0,0,0.0,0.0,0.0
+1207,Prepare to cut cardboard,0,0,0.0,0.0,0.0
+1208,Score cardboard,0,0,0.0,0.0,0.0
+1209,Move cardboard sheet,0,0,0.0,0.0,0.0
+1210,Trim cardboard,0,0,0.0,0.0,0.0