Add files using upload-large-folder tool

data/episode128_task_model_radar.json

@@ -1,7 +1,7 @@
 {
   "title": "128-Episode 20-Task Radar",
   "status": "pass",
-  "generated_at_utc": "2026-06-21T10:47:17+00:00",
+  "generated_at_utc": "2026-06-21T15:20:34+00:00",
   "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3-Omni v6, Cosmos3-Super, and Cosmos3-Nano diagnostics. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.",
   "task_count": 20,
   "method_count": 7,
@@ -192,7 +192,7 @@
       "label": "Action Recognition",
       "axis_label": "01 Action Recognition",
       "short_label": "Action",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -283,7 +283,7 @@
       "label": "Procedure Step Recognition",
       "axis_label": "02 Procedure Step Recognition",
       "short_label": "Step",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -374,7 +374,7 @@
       "label": "Action Boundary Detection",
       "axis_label": "03 Action Boundary Detection",
       "short_label": "Boundary",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -465,7 +465,7 @@
       "label": "Next-Action Prediction",
       "axis_label": "04 Next-Action Prediction",
       "short_label": "Next act",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -556,7 +556,7 @@
       "label": "Hand Trajectory Forecasting",
       "axis_label": "05 Hand Trajectory Forecasting",
       "short_label": "Hand traj",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "mpjpe",
       "metric_name": "MPJPE",
       "metric_direction": "lower",
@@ -647,7 +647,7 @@
       "label": "Contact State Prediction",
       "axis_label": "06 Contact State Prediction",
       "short_label": "Contact",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -738,7 +738,7 @@
       "label": "Object Relevance Prediction",
       "axis_label": "07 Object Relevance Prediction",
       "short_label": "Objects",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "micro_f1",
       "metric_name": "micro-F1",
       "metric_direction": "higher",
@@ -829,7 +829,7 @@
       "label": "Language Grounding",
       "axis_label": "08 Language Grounding",
       "short_label": "Language",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "mrr",
       "metric_name": "MRR",
       "metric_direction": "higher",
@@ -920,7 +920,7 @@
       "label": "Cross-Modal Retrieval",
       "axis_label": "09 Cross-Modal Retrieval",
       "short_label": "X-modal",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "mrr",
       "metric_name": "MRR",
       "metric_direction": "higher",
@@ -1011,7 +1011,7 @@
       "label": "Cross-Modal Reconstruction",
       "axis_label": "10 Cross-Modal Reconstruction",
       "short_label": "Recon",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "r2",
       "metric_name": "R2",
       "metric_direction": "higher",
@@ -1102,7 +1102,7 @@
       "label": "Temporal Order Verification",
       "axis_label": "11 Temporal Order Verification",
       "short_label": "Order",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "f1",
       "metric_name": "F1",
       "metric_direction": "higher",
@@ -1193,7 +1193,7 @@
       "label": "Multimodal Synchronization Detection",
       "axis_label": "12 Multimodal Synchronization Detection",
       "short_label": "Sync",
-      "origin": "original_public_sample_tasks",
+      "provenance_source": "walkthrough_backed_task_contract",
       "metric_key": "f1",
       "metric_name": "F1",
       "metric_direction": "higher",
@@ -1284,7 +1284,7 @@
       "label": "Long-Horizon Next-Action Forecasting",
       "axis_label": "13 Long-Horizon Next-Action Forecasting",
       "short_label": "Long act",
-      "origin": "additional_public_sample_tasks",
+      "provenance_source": "historical_result_bundle",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -1375,7 +1375,7 @@
       "label": "Long-Horizon Next-Subtask Forecasting",
       "axis_label": "14 Long-Horizon Next-Subtask Forecasting",
       "short_label": "Long step",
-      "origin": "additional_public_sample_tasks",
+      "provenance_source": "historical_result_bundle",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -1466,7 +1466,7 @@
       "label": "Interaction Text Prediction",
       "axis_label": "15 Interaction Text Prediction",
       "short_label": "Interact txt",
-      "origin": "additional_public_sample_tasks",
+      "provenance_source": "historical_result_bundle",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -1557,7 +1557,7 @@
       "label": "Action-Object Relation Prediction",
       "axis_label": "16 Action-Object Relation Prediction",
       "short_label": "Act+obj",
-      "origin": "additional_public_sample_tasks",
+      "provenance_source": "historical_result_bundle",
       "metric_key": "macro_f1",
       "metric_name": "macro-F1",
       "metric_direction": "higher",
@@ -1648,7 +1648,7 @@
       "label": "Future Object-Set Forecasting",
       "axis_label": "17 Future Object-Set Forecasting",
       "short_label": "Future obj",
-      "origin": "additional_public_sample_tasks",
+      "provenance_source": "historical_result_bundle",
       "metric_key": "micro_f1",
       "metric_name": "micro-F1",
       "metric_direction": "higher",
@@ -1739,7 +1739,7 @@
       "label": "IMU-to-Hand Pose Reconstruction",
       "axis_label": "18 IMU-to-Hand Pose Reconstruction",
       "short_label": "IMU->hand",
-      "origin": "additional_public_sample_tasks",
+      "provenance_source": "historical_result_bundle",
       "metric_key": "mae",
       "metric_name": "MAE",
       "metric_direction": "lower",
@@ -1830,7 +1830,7 @@
       "label": "Camera-View Synchronization Retrieval",
       "axis_label": "19 Camera-View Synchronization Retrieval",
       "short_label": "Cam sync",
-      "origin": "additional_public_sample_tasks",
+      "provenance_source": "historical_result_bundle",
       "metric_key": "mrr",
       "metric_name": "MRR",
       "metric_direction": "higher",
@@ -1921,7 +1921,7 @@
       "label": "Time-to-Next-Transition Regression",
       "axis_label": "20 Time-to-Next-Transition Regression",
       "short_label": "Time2bdry",
-      "origin": "additional_public_sample_tasks",
+      "provenance_source": "historical_result_bundle",
       "metric_key": "mae",
       "metric_name": "MAE frames",
       "metric_direction": "lower",