Robotics
PyTorch
Cosmos
xperience10m_task_baseline_suite
embodied-ai
multimodal
xperience-10m
baseline
evaluation
qwen3-omni
Instructions to use cy0307/ropedia-xperience-10m-task-baselines with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use cy0307/ropedia-xperience-10m-task-baselines with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Add files using upload-large-folder tool
Browse files- data/artifact_index.json +62 -62
- data/episode128_task_model_radar.json +46 -11
- data/public_surface_qa.json +9 -9
- data/quality_gates.json +1 -1
- data/scope_claims_audit.json +1 -1
- data/single_episode_task_model_radar.json +24 -6
- data/source_alignment_audit.json +1 -1
- data/task_method_20_result_matrix.json +10 -10
- data/task_surface_integrity.json +1 -1
- data/website_integrity.json +16 -16
data/artifact_index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"title": "Ropedia Xperience-10M Task Suite Artifact Index",
|
| 3 |
-
"generated_at_utc": "2026-06-
|
| 4 |
"status": "pass",
|
| 5 |
"artifact_count": 228,
|
| 6 |
"missing": [],
|
|
@@ -92,8 +92,8 @@
|
|
| 92 |
"surface": "repo_hf",
|
| 93 |
"shows": "Defines terminology that can be confused across data scope, task metrics, model branches, and public mirrors.",
|
| 94 |
"exists": true,
|
| 95 |
-
"bytes":
|
| 96 |
-
"sha256": "
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"id": "glossary_json",
|
|
@@ -103,8 +103,8 @@
|
|
| 103 |
"surface": "website_hf",
|
| 104 |
"shows": "Machine-readable terminology layer for the website, artifact dataset, model mirror, and public QA checks.",
|
| 105 |
"exists": true,
|
| 106 |
-
"bytes":
|
| 107 |
-
"sha256": "
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"id": "research_roadmap",
|
|
@@ -158,8 +158,8 @@
|
|
| 158 |
"surface": "repo_hf",
|
| 159 |
"shows": "Frames spatial intelligence, human-video world modeling, and vision-language-action as three pipeline tracks with explicit inputs, outputs, maturity, and next evidence gates.",
|
| 160 |
"exists": true,
|
| 161 |
-
"bytes":
|
| 162 |
-
"sha256": "
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"id": "three_foundation_pipelines_json",
|
|
@@ -169,8 +169,8 @@
|
|
| 169 |
"surface": "website_hf",
|
| 170 |
"shows": "Machine-readable pipeline-track contract for the website and Hugging Face mirrors.",
|
| 171 |
"exists": true,
|
| 172 |
-
"bytes":
|
| 173 |
-
"sha256": "
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"id": "spatial_intelligence_slide_diagram",
|
|
@@ -632,7 +632,7 @@
|
|
| 632 |
"shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
|
| 633 |
"exists": true,
|
| 634 |
"bytes": 4432,
|
| 635 |
-
"sha256": "
|
| 636 |
},
|
| 637 |
{
|
| 638 |
"id": "source_alignment_validator",
|
|
@@ -653,8 +653,8 @@
|
|
| 653 |
"surface": "repo_hf",
|
| 654 |
"shows": "Publishes prepared Space, artifact dataset, and model bundles, including an explicit model-binary upload batch.",
|
| 655 |
"exists": true,
|
| 656 |
-
"bytes":
|
| 657 |
-
"sha256": "
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"id": "github_package_dockerfile",
|
|
@@ -697,8 +697,8 @@
|
|
| 697 |
"surface": "website_hf",
|
| 698 |
"shows": "Machine-readable protocol generated from committed task metrics for website and HF mirrors.",
|
| 699 |
"exists": true,
|
| 700 |
-
"bytes":
|
| 701 |
-
"sha256": "
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"id": "evaluation_protocol_builder",
|
|
@@ -708,8 +708,8 @@
|
|
| 708 |
"surface": "repo_hf",
|
| 709 |
"shows": "Regenerates the protocol from committed summary metrics and task artifacts.",
|
| 710 |
"exists": true,
|
| 711 |
-
"bytes":
|
| 712 |
-
"sha256": "
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"id": "task_suite_20",
|
|
@@ -730,8 +730,8 @@
|
|
| 730 |
"surface": "website_hf",
|
| 731 |
"shows": "Machine-readable unified 20-task index for the website, Hugging Face mirrors, and live verification.",
|
| 732 |
"exists": true,
|
| 733 |
-
"bytes":
|
| 734 |
-
"sha256": "
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"id": "task_suite_20_builder",
|
|
@@ -741,8 +741,8 @@
|
|
| 741 |
"surface": "repo_hf",
|
| 742 |
"shows": "Regenerates the unified 20-task JSON and Markdown from the public-sample metrics plus the historical provenance result bundle.",
|
| 743 |
"exists": true,
|
| 744 |
-
"bytes":
|
| 745 |
-
"sha256": "
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"id": "unified_task_model_radar_json",
|
|
@@ -750,10 +750,10 @@
|
|
| 750 |
"path": "docs/data/unified_task_model_radar.json",
|
| 751 |
"kind": "website_data",
|
| 752 |
"surface": "website_hf",
|
| 753 |
-
"shows": "Stores normalized 20-axis radar values, raw task metrics, Qwen3-Omni/Cosmos3
|
| 754 |
"exists": true,
|
| 755 |
-
"bytes":
|
| 756 |
-
"sha256": "
|
| 757 |
},
|
| 758 |
{
|
| 759 |
"id": "single_episode_task_model_radar_json",
|
|
@@ -763,8 +763,8 @@
|
|
| 763 |
"surface": "website_hf",
|
| 764 |
"shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
|
| 765 |
"exists": true,
|
| 766 |
-
"bytes":
|
| 767 |
-
"sha256": "
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"id": "episode128_task_model_radar_json",
|
|
@@ -774,8 +774,8 @@
|
|
| 774 |
"surface": "website_hf",
|
| 775 |
"shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines, Qwen3-Omni v6, Cosmos3-Super, and Cosmos3-Nano, now complete at 140/140 scored rows with proxy notes retained.",
|
| 776 |
"exists": true,
|
| 777 |
-
"bytes":
|
| 778 |
-
"sha256": "
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": "task_method_20_result_matrix_json",
|
|
@@ -785,8 +785,8 @@
|
|
| 785 |
"surface": "website_hf",
|
| 786 |
"shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and the current release is complete at 180/180 scored rows.",
|
| 787 |
"exists": true,
|
| 788 |
-
"bytes":
|
| 789 |
-
"sha256": "
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"id": "task_method_20_result_matrix",
|
|
@@ -796,8 +796,8 @@
|
|
| 796 |
"surface": "repo_hf",
|
| 797 |
"shows": "Reader-facing table that separates 20 records per method, direct numeric scores, documented compact-proxy scores, and source artifacts.",
|
| 798 |
"exists": true,
|
| 799 |
-
"bytes":
|
| 800 |
-
"sha256": "
|
| 801 |
},
|
| 802 |
{
|
| 803 |
"id": "task_method_20_gap_audit_json",
|
|
@@ -808,7 +808,7 @@
|
|
| 808 |
"shows": "Machine-readable 180-record completion ledger with numeric scores, proxy flags, explicit status reasons, and source artifacts.",
|
| 809 |
"exists": true,
|
| 810 |
"bytes": 8500,
|
| 811 |
-
"sha256": "
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"id": "task_method_20_gap_audit",
|
|
@@ -819,7 +819,7 @@
|
|
| 819 |
"shows": "Reader-facing ledger confirming 180/180 scored method-task cells and listing the six compact-proxy records separately.",
|
| 820 |
"exists": true,
|
| 821 |
"bytes": 3417,
|
| 822 |
-
"sha256": "
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"id": "task_method_20_source_audit_json",
|
|
@@ -830,7 +830,7 @@
|
|
| 830 |
"shows": "Machine-readable check that scored JSON-backed matrix cells match their declared metric source values.",
|
| 831 |
"exists": true,
|
| 832 |
"bytes": 561,
|
| 833 |
-
"sha256": "
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"id": "task_method_20_source_audit",
|
|
@@ -841,7 +841,7 @@
|
|
| 841 |
"shows": "Reader-facing source-value audit for the 180-result matrix.",
|
| 842 |
"exists": true,
|
| 843 |
"bytes": 447,
|
| 844 |
-
"sha256": "
|
| 845 |
},
|
| 846 |
{
|
| 847 |
"id": "two_evidence_line_map_chart",
|
|
@@ -860,10 +860,10 @@
|
|
| 860 |
"path": "docs/assets/charts/unified_task_model_radar.svg",
|
| 861 |
"kind": "generated_figure",
|
| 862 |
"surface": "website_hf",
|
| 863 |
-
"shows": "
|
| 864 |
"exists": true,
|
| 865 |
-
"bytes":
|
| 866 |
-
"sha256": "
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"id": "single_episode_task_model_radar_chart",
|
|
@@ -871,10 +871,10 @@
|
|
| 871 |
"path": "docs/assets/charts/single_episode_task_model_radar.svg",
|
| 872 |
"kind": "generated_figure",
|
| 873 |
"surface": "website_hf",
|
| 874 |
-
"shows": "
|
| 875 |
"exists": true,
|
| 876 |
-
"bytes":
|
| 877 |
-
"sha256": "
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": "episode128_task_model_radar_chart",
|
|
@@ -882,10 +882,10 @@
|
|
| 882 |
"path": "docs/assets/charts/episode128_task_model_radar.svg",
|
| 883 |
"kind": "generated_figure",
|
| 884 |
"surface": "website_hf",
|
| 885 |
-
"shows": "Separates
|
| 886 |
"exists": true,
|
| 887 |
-
"bytes":
|
| 888 |
-
"sha256": "
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"id": "unified_task_model_radar_builder",
|
|
@@ -893,10 +893,10 @@
|
|
| 893 |
"path": "scripts/build_unified_task_model_radar.py",
|
| 894 |
"kind": "visualization_builder",
|
| 895 |
"surface": "repo_hf",
|
| 896 |
-
"shows": "Regenerates
|
| 897 |
"exists": true,
|
| 898 |
-
"bytes":
|
| 899 |
-
"sha256": "
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"id": "task_method_20_gap_audit_builder",
|
|
@@ -1093,8 +1093,8 @@
|
|
| 1093 |
"surface": "repo_hf",
|
| 1094 |
"shows": "Catalogs public figures, charts, modality thumbnails, dimensions, hashes, roles, and source scripts.",
|
| 1095 |
"exists": true,
|
| 1096 |
-
"bytes":
|
| 1097 |
-
"sha256": "
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
"id": "figure_index_json",
|
|
@@ -1104,8 +1104,8 @@
|
|
| 1104 |
"surface": "website_hf",
|
| 1105 |
"shows": "Machine-readable visual asset index for website and Hugging Face mirrors.",
|
| 1106 |
"exists": true,
|
| 1107 |
-
"bytes":
|
| 1108 |
-
"sha256": "
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"id": "figure_index_builder",
|
|
@@ -1115,8 +1115,8 @@
|
|
| 1115 |
"surface": "repo_hf",
|
| 1116 |
"shows": "Regenerates visual-asset hashes, dimensions, and source-script provenance.",
|
| 1117 |
"exists": true,
|
| 1118 |
-
"bytes":
|
| 1119 |
-
"sha256": "
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"id": "brand_assets_json",
|
|
@@ -1182,7 +1182,7 @@
|
|
| 1182 |
"shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
|
| 1183 |
"exists": true,
|
| 1184 |
"bytes": 8640,
|
| 1185 |
-
"sha256": "
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"id": "public_surface_qa",
|
|
@@ -1226,7 +1226,7 @@
|
|
| 1226 |
"volatile": true,
|
| 1227 |
"shows": "Machine-readable report for SEO/social metadata, accessible tab semantics, public links, project links, and clear project presentation.",
|
| 1228 |
"exists": true,
|
| 1229 |
-
"bytes":
|
| 1230 |
"hash_policy": "existence_and_size_only"
|
| 1231 |
},
|
| 1232 |
{
|
|
@@ -1318,8 +1318,8 @@
|
|
| 1318 |
"surface": "repo",
|
| 1319 |
"shows": "Fetches the published GitHub/HF URLs and compares live hashes and public-card markers against the release assets.",
|
| 1320 |
"exists": true,
|
| 1321 |
-
"bytes":
|
| 1322 |
-
"sha256": "
|
| 1323 |
},
|
| 1324 |
{
|
| 1325 |
"id": "reproducibility_contract",
|
|
@@ -1351,8 +1351,8 @@
|
|
| 1351 |
"surface": "repo_hf",
|
| 1352 |
"shows": "Generates the selective artifact catalog from local files.",
|
| 1353 |
"exists": true,
|
| 1354 |
-
"bytes":
|
| 1355 |
-
"sha256": "
|
| 1356 |
},
|
| 1357 |
{
|
| 1358 |
"id": "publication_audit",
|
|
@@ -1363,7 +1363,7 @@
|
|
| 1363 |
"volatile": true,
|
| 1364 |
"shows": "Confirms public bundles exclude raw data, caches, heavy archives, and credential text.",
|
| 1365 |
"exists": true,
|
| 1366 |
-
"bytes":
|
| 1367 |
"hash_policy": "existence_and_size_only"
|
| 1368 |
},
|
| 1369 |
{
|
|
@@ -1387,7 +1387,7 @@
|
|
| 1387 |
"volatile": true,
|
| 1388 |
"shows": "Confirms prepared GitHub/HF Space/artifact/model mirrors share the same critical data, figure, website HTML, and validator files.",
|
| 1389 |
"exists": true,
|
| 1390 |
-
"bytes":
|
| 1391 |
"hash_policy": "existence_and_size_only"
|
| 1392 |
},
|
| 1393 |
{
|
|
@@ -1399,7 +1399,7 @@
|
|
| 1399 |
"volatile": true,
|
| 1400 |
"shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
|
| 1401 |
"exists": true,
|
| 1402 |
-
"bytes":
|
| 1403 |
"hash_policy": "existence_and_size_only"
|
| 1404 |
},
|
| 1405 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"title": "Ropedia Xperience-10M Task Suite Artifact Index",
|
| 3 |
+
"generated_at_utc": "2026-06-21T20:35:18+00:00",
|
| 4 |
"status": "pass",
|
| 5 |
"artifact_count": 228,
|
| 6 |
"missing": [],
|
|
|
|
| 92 |
"surface": "repo_hf",
|
| 93 |
"shows": "Defines terminology that can be confused across data scope, task metrics, model branches, and public mirrors.",
|
| 94 |
"exists": true,
|
| 95 |
+
"bytes": 10857,
|
| 96 |
+
"sha256": "b9b8f8695b6c211e849073e1634057f158877a61161eca05b1266769158ee83e"
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"id": "glossary_json",
|
|
|
|
| 103 |
"surface": "website_hf",
|
| 104 |
"shows": "Machine-readable terminology layer for the website, artifact dataset, model mirror, and public QA checks.",
|
| 105 |
"exists": true,
|
| 106 |
+
"bytes": 18754,
|
| 107 |
+
"sha256": "b1dc42e1f42a7c19bb4b2ebd32a0862df28bec671eaa849b09a97f103675e9eb"
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"id": "research_roadmap",
|
|
|
|
| 158 |
"surface": "repo_hf",
|
| 159 |
"shows": "Frames spatial intelligence, human-video world modeling, and vision-language-action as three pipeline tracks with explicit inputs, outputs, maturity, and next evidence gates.",
|
| 160 |
"exists": true,
|
| 161 |
+
"bytes": 11609,
|
| 162 |
+
"sha256": "69d4d8781015c807c58a720b3bf967ee872540a2fe2b7e7973105946c5a1cf11"
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"id": "three_foundation_pipelines_json",
|
|
|
|
| 169 |
"surface": "website_hf",
|
| 170 |
"shows": "Machine-readable pipeline-track contract for the website and Hugging Face mirrors.",
|
| 171 |
"exists": true,
|
| 172 |
+
"bytes": 14465,
|
| 173 |
+
"sha256": "c8c9b7a9ee8d3ecfe8662cf0336a7ca2ade6d670c5567d2a50dfb67c7241defd"
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"id": "spatial_intelligence_slide_diagram",
|
|
|
|
| 632 |
"shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
|
| 633 |
"exists": true,
|
| 634 |
"bytes": 4432,
|
| 635 |
+
"sha256": "2f3d03a1c56ebb1b220574e565a05d35705a10a22d1cb7ecdcb1452630574bc9"
|
| 636 |
},
|
| 637 |
{
|
| 638 |
"id": "source_alignment_validator",
|
|
|
|
| 653 |
"surface": "repo_hf",
|
| 654 |
"shows": "Publishes prepared Space, artifact dataset, and model bundles, including an explicit model-binary upload batch.",
|
| 655 |
"exists": true,
|
| 656 |
+
"bytes": 29935,
|
| 657 |
+
"sha256": "89ed1b25784cd42f19f2e4731eaa52e8655e8ed06cc2a12b6a2c0add027c5fc0"
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"id": "github_package_dockerfile",
|
|
|
|
| 697 |
"surface": "website_hf",
|
| 698 |
"shows": "Machine-readable protocol generated from committed task metrics for website and HF mirrors.",
|
| 699 |
"exists": true,
|
| 700 |
+
"bytes": 24267,
|
| 701 |
+
"sha256": "83289b52e0193fa86d63fac7dd8af98d0612199b1e1a5f5ed37014baa9168656"
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"id": "evaluation_protocol_builder",
|
|
|
|
| 708 |
"surface": "repo_hf",
|
| 709 |
"shows": "Regenerates the protocol from committed summary metrics and task artifacts.",
|
| 710 |
"exists": true,
|
| 711 |
+
"bytes": 19845,
|
| 712 |
+
"sha256": "b5d888fd67ba6b8150b24960aa0858db50f16a5c7b59a8ce274401e384f0a2a3"
|
| 713 |
},
|
| 714 |
{
|
| 715 |
"id": "task_suite_20",
|
|
|
|
| 730 |
"surface": "website_hf",
|
| 731 |
"shows": "Machine-readable unified 20-task index for the website, Hugging Face mirrors, and live verification.",
|
| 732 |
"exists": true,
|
| 733 |
+
"bytes": 34805,
|
| 734 |
+
"sha256": "5d7a3b5b57e64980291b3ce6a8741b0b822e94bd447ca95519d1da7040923476"
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"id": "task_suite_20_builder",
|
|
|
|
| 741 |
"surface": "repo_hf",
|
| 742 |
"shows": "Regenerates the unified 20-task JSON and Markdown from the public-sample metrics plus the historical provenance result bundle.",
|
| 743 |
"exists": true,
|
| 744 |
+
"bytes": 12129,
|
| 745 |
+
"sha256": "4c2550c657bfa5bc37e21e78e7e27dd70daa3b178c8ffb3191e52f835221713a"
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"id": "unified_task_model_radar_json",
|
|
|
|
| 750 |
"path": "docs/data/unified_task_model_radar.json",
|
| 751 |
"kind": "website_data",
|
| 752 |
"surface": "website_hf",
|
| 753 |
+
"shows": "Stores normalized 20-axis radar values, raw task metrics, grouped chart-design metadata, Qwen3-Omni/Cosmos3 source mappings, method-card caveats, proxy flags, and source artifacts.",
|
| 754 |
"exists": true,
|
| 755 |
+
"bytes": 230938,
|
| 756 |
+
"sha256": "bd7b8fd8a169273c5cec2beab050a583307dcc64e5e3fefcd690484b4a0754bc"
|
| 757 |
},
|
| 758 |
{
|
| 759 |
"id": "single_episode_task_model_radar_json",
|
|
|
|
| 763 |
"surface": "website_hf",
|
| 764 |
"shows": "Machine-readable split radar for the one-episode Minimal and Neural MLP baselines, both scored on all 20 task contracts.",
|
| 765 |
"exists": true,
|
| 766 |
+
"bytes": 52256,
|
| 767 |
+
"sha256": "f282dc0c4c654fe6f2cd646612fd0942d267dec60c6143cc36688edbc27c13da"
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"id": "episode128_task_model_radar_json",
|
|
|
|
| 774 |
"surface": "website_hf",
|
| 775 |
"shows": "Machine-readable split radar for selected 128-episode metadata/raw baselines, Qwen3-Omni v6, Cosmos3-Super, and Cosmos3-Nano, now complete at 140/140 scored rows with proxy notes retained.",
|
| 776 |
"exists": true,
|
| 777 |
+
"bytes": 186828,
|
| 778 |
+
"sha256": "f904cf9eb3160a50e4469989e44557e77d710e459f812ba7b194d0ed8d9746bd"
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"id": "task_method_20_result_matrix_json",
|
|
|
|
| 785 |
"surface": "website_hf",
|
| 786 |
"shows": "Machine-readable 9-method by 20-task matrix where every method has 20 records and the current release is complete at 180/180 scored rows.",
|
| 787 |
"exists": true,
|
| 788 |
+
"bytes": 128991,
|
| 789 |
+
"sha256": "bacb549e64b6d1936b55fe7593cfbaeb1dbf5bfe824c8507ea75e493230212fe"
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"id": "task_method_20_result_matrix",
|
|
|
|
| 796 |
"surface": "repo_hf",
|
| 797 |
"shows": "Reader-facing table that separates 20 records per method, direct numeric scores, documented compact-proxy scores, and source artifacts.",
|
| 798 |
"exists": true,
|
| 799 |
+
"bytes": 14862,
|
| 800 |
+
"sha256": "a6f769d40ed22a2d63dad88029be393d55ed9af3082ab61fc1ad8b314aa871a6"
|
| 801 |
},
|
| 802 |
{
|
| 803 |
"id": "task_method_20_gap_audit_json",
|
|
|
|
| 808 |
"shows": "Machine-readable 180-record completion ledger with numeric scores, proxy flags, explicit status reasons, and source artifacts.",
|
| 809 |
"exists": true,
|
| 810 |
"bytes": 8500,
|
| 811 |
+
"sha256": "4f5cc7a29fe030a9fd5b97893ac67454ebc6287f5942aeedb2bfca71c411332d"
|
| 812 |
},
|
| 813 |
{
|
| 814 |
"id": "task_method_20_gap_audit",
|
|
|
|
| 819 |
"shows": "Reader-facing ledger confirming 180/180 scored method-task cells and listing the six compact-proxy records separately.",
|
| 820 |
"exists": true,
|
| 821 |
"bytes": 3417,
|
| 822 |
+
"sha256": "b094732dd98c904ea0ab30e741576a3d5eeb8ca07e7a494e459b11e31320ae4d"
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"id": "task_method_20_source_audit_json",
|
|
|
|
| 830 |
"shows": "Machine-readable check that scored JSON-backed matrix cells match their declared metric source values.",
|
| 831 |
"exists": true,
|
| 832 |
"bytes": 561,
|
| 833 |
+
"sha256": "1bc6bb15ab45e73ada4d3c2d1ec326cffd9c6bc6d6d791c7468b3ed16881a463"
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"id": "task_method_20_source_audit",
|
|
|
|
| 841 |
"shows": "Reader-facing source-value audit for the 180-result matrix.",
|
| 842 |
"exists": true,
|
| 843 |
"bytes": 447,
|
| 844 |
+
"sha256": "7f5e80d6dcd66be1c6b2c63144adb64d0cdad0008884ebd8f015388545e4b914"
|
| 845 |
},
|
| 846 |
{
|
| 847 |
"id": "two_evidence_line_map_chart",
|
|
|
|
| 860 |
"path": "docs/assets/charts/unified_task_model_radar.svg",
|
| 861 |
"kind": "generated_figure",
|
| 862 |
"surface": "website_hf",
|
| 863 |
+
"shows": "Groups all nine methods into small-multiple 20-task radar panels so single-episode, 128-episode metadata/text, 128-episode raw-feature, and foundation-model rows remain readable.",
|
| 864 |
"exists": true,
|
| 865 |
+
"bytes": 98527,
|
| 866 |
+
"sha256": "5b034b22d2a772a57e7db50f300cb70d00bd31ac89d0c039c16ac8c23a5137ec"
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"id": "single_episode_task_model_radar_chart",
|
|
|
|
| 871 |
"path": "docs/assets/charts/single_episode_task_model_radar.svg",
|
| 872 |
"kind": "generated_figure",
|
| 873 |
"surface": "website_hf",
|
| 874 |
+
"shows": "Shows the one-episode Minimal and Neural MLP 20/20 scored baselines in one enlarged radar panel with local legend and task key.",
|
| 875 |
"exists": true,
|
| 876 |
+
"bytes": 36930,
|
| 877 |
+
"sha256": "96e609b0577e66db0ee8c63939c11b1fb28018285a1d259362de0bff415cc939"
|
| 878 |
},
|
| 879 |
{
|
| 880 |
"id": "episode128_task_model_radar_chart",
|
|
|
|
| 882 |
"path": "docs/assets/charts/episode128_task_model_radar.svg",
|
| 883 |
"kind": "generated_figure",
|
| 884 |
"surface": "website_hf",
|
| 885 |
+
"shows": "Separates selected 128-episode methods into metadata/text, raw-feature, and foundation-model radar panels with all 140 result rows scored and proxy notes retained.",
|
| 886 |
"exists": true,
|
| 887 |
+
"bytes": 79370,
|
| 888 |
+
"sha256": "5151c8aca22bd4aeda60b143b1164c1d1b9eb4babbeabf6da598701ccbbbf5c9"
|
| 889 |
},
|
| 890 |
{
|
| 891 |
"id": "unified_task_model_radar_builder",
|
|
|
|
| 893 |
"path": "scripts/build_unified_task_model_radar.py",
|
| 894 |
"kind": "visualization_builder",
|
| 895 |
"surface": "repo_hf",
|
| 896 |
+
"shows": "Regenerates grouped 20-task radar charts plus machine-readable metric, source, chart-design, and proxy metadata.",
|
| 897 |
"exists": true,
|
| 898 |
+
"bytes": 79396,
|
| 899 |
+
"sha256": "78949d7030cf6995edbb1d46a35692c7fe835d102df619cdf8c9d8ea9c5318e2"
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"id": "task_method_20_gap_audit_builder",
|
|
|
|
| 1093 |
"surface": "repo_hf",
|
| 1094 |
"shows": "Catalogs public figures, charts, modality thumbnails, dimensions, hashes, roles, and source scripts.",
|
| 1095 |
"exists": true,
|
| 1096 |
+
"bytes": 7068,
|
| 1097 |
+
"sha256": "cc64c0bb070e7eb0035ba590a6d83ed07fcc68fb56081668caebf40b49b9900f"
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
"id": "figure_index_json",
|
|
|
|
| 1104 |
"surface": "website_hf",
|
| 1105 |
"shows": "Machine-readable visual asset index for website and Hugging Face mirrors.",
|
| 1106 |
"exists": true,
|
| 1107 |
+
"bytes": 19526,
|
| 1108 |
+
"sha256": "601acd715891bb148b0a1706573a2fdb015ca3c5967f02a169577b483b0dcd43"
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"id": "figure_index_builder",
|
|
|
|
| 1115 |
"surface": "repo_hf",
|
| 1116 |
"shows": "Regenerates visual-asset hashes, dimensions, and source-script provenance.",
|
| 1117 |
"exists": true,
|
| 1118 |
+
"bytes": 16886,
|
| 1119 |
+
"sha256": "fc44ea60b6f491d290a56d4c1097fcfc37c024f8a9bc3b3db013252f45d96e64"
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"id": "brand_assets_json",
|
|
|
|
| 1182 |
"shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
|
| 1183 |
"exists": true,
|
| 1184 |
"bytes": 8640,
|
| 1185 |
+
"sha256": "87c26049df761996430f1ca6ef25ee53400387f907f356dcea6b3fcc7d6dac82"
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"id": "public_surface_qa",
|
|
|
|
| 1226 |
"volatile": true,
|
| 1227 |
"shows": "Machine-readable report for SEO/social metadata, accessible tab semantics, public links, project links, and clear project presentation.",
|
| 1228 |
"exists": true,
|
| 1229 |
+
"bytes": 7693,
|
| 1230 |
"hash_policy": "existence_and_size_only"
|
| 1231 |
},
|
| 1232 |
{
|
|
|
|
| 1318 |
"surface": "repo",
|
| 1319 |
"shows": "Fetches the published GitHub/HF URLs and compares live hashes and public-card markers against the release assets.",
|
| 1320 |
"exists": true,
|
| 1321 |
+
"bytes": 69123,
|
| 1322 |
+
"sha256": "a96d0a95ea1da54fb8b6a95b2c91d4a067eef8358d825c44d919e66d78ecb8f7"
|
| 1323 |
},
|
| 1324 |
{
|
| 1325 |
"id": "reproducibility_contract",
|
|
|
|
| 1351 |
"surface": "repo_hf",
|
| 1352 |
"shows": "Generates the selective artifact catalog from local files.",
|
| 1353 |
"exists": true,
|
| 1354 |
+
"bytes": 68407,
|
| 1355 |
+
"sha256": "9f5fc1af7c4c23083975066691bf6d75aa99280961198e2c47be88754c142418"
|
| 1356 |
},
|
| 1357 |
{
|
| 1358 |
"id": "publication_audit",
|
|
|
|
| 1363 |
"volatile": true,
|
| 1364 |
"shows": "Confirms public bundles exclude raw data, caches, heavy archives, and credential text.",
|
| 1365 |
"exists": true,
|
| 1366 |
+
"bytes": 10940,
|
| 1367 |
"hash_policy": "existence_and_size_only"
|
| 1368 |
},
|
| 1369 |
{
|
|
|
|
| 1387 |
"volatile": true,
|
| 1388 |
"shows": "Confirms prepared GitHub/HF Space/artifact/model mirrors share the same critical data, figure, website HTML, and validator files.",
|
| 1389 |
"exists": true,
|
| 1390 |
+
"bytes": 1420751,
|
| 1391 |
"hash_policy": "existence_and_size_only"
|
| 1392 |
},
|
| 1393 |
{
|
|
|
|
| 1399 |
"volatile": true,
|
| 1400 |
"shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
|
| 1401 |
"exists": true,
|
| 1402 |
+
"bytes": 20178,
|
| 1403 |
"hash_policy": "existence_and_size_only"
|
| 1404 |
},
|
| 1405 |
{
|
data/episode128_task_model_radar.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"title": "128-Episode 20-Task Radar",
|
| 3 |
"status": "pass",
|
| 4 |
-
"generated_at_utc": "2026-06-
|
| 5 |
"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.",
|
| 6 |
"task_count": 20,
|
| 7 |
"method_count": 7,
|
|
@@ -11,10 +11,45 @@
|
|
| 11 |
"higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
|
| 12 |
"lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
|
| 13 |
"raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
|
|
|
|
| 14 |
"result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
|
| 15 |
-
"foundation_model_overlay": "Qwen3-Omni and Cosmos3
|
| 16 |
-
"metadata_128_overlay": "128-episode aligned baselines
|
| 17 |
-
"raw_128_overlay": "128-episode raw-feature baselines
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
},
|
| 19 |
"source_unified_radar": "docs/data/unified_task_model_radar.json",
|
| 20 |
"source_result_matrix": "docs/data/task_method_20_result_matrix.json",
|
|
@@ -28,7 +63,7 @@
|
|
| 28 |
"scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
|
| 29 |
"stroke_dasharray": "9 6",
|
| 30 |
"method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
|
| 31 |
-
"plotted_as": "
|
| 32 |
"result_record_count": 20,
|
| 33 |
"scored_task_count": 20,
|
| 34 |
"covered_task_count": 20,
|
|
@@ -52,7 +87,7 @@
|
|
| 52 |
"scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
|
| 53 |
"stroke_dasharray": "3 6",
|
| 54 |
"method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
|
| 55 |
-
"plotted_as": "
|
| 56 |
"result_record_count": 20,
|
| 57 |
"scored_task_count": 20,
|
| 58 |
"covered_task_count": 20,
|
|
@@ -76,7 +111,7 @@
|
|
| 76 |
"scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
|
| 77 |
"stroke_dasharray": "8 4",
|
| 78 |
"method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
|
| 79 |
-
"plotted_as": "
|
| 80 |
"result_record_count": 20,
|
| 81 |
"scored_task_count": 20,
|
| 82 |
"covered_task_count": 20,
|
|
@@ -100,7 +135,7 @@
|
|
| 100 |
"scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
|
| 101 |
"stroke_dasharray": "2 5",
|
| 102 |
"method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
|
| 103 |
-
"plotted_as": "
|
| 104 |
"result_record_count": 20,
|
| 105 |
"scored_task_count": 20,
|
| 106 |
"covered_task_count": 20,
|
|
@@ -124,7 +159,7 @@
|
|
| 124 |
"scope": "128 selected episodes, held-out test",
|
| 125 |
"stroke_dasharray": "7 7",
|
| 126 |
"method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
|
| 127 |
-
"plotted_as": "
|
| 128 |
"result_record_count": 20,
|
| 129 |
"scored_task_count": 20,
|
| 130 |
"covered_task_count": 20,
|
|
@@ -147,7 +182,7 @@
|
|
| 147 |
"scope": "128 selected episodes, held-out test",
|
| 148 |
"stroke_dasharray": "4 7",
|
| 149 |
"method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
|
| 150 |
-
"plotted_as": "
|
| 151 |
"result_record_count": 20,
|
| 152 |
"scored_task_count": 20,
|
| 153 |
"covered_task_count": 20,
|
|
@@ -170,7 +205,7 @@
|
|
| 170 |
"scope": "128 selected episodes, held-out test",
|
| 171 |
"stroke_dasharray": "2 7",
|
| 172 |
"method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
|
| 173 |
-
"plotted_as": "
|
| 174 |
"result_record_count": 20,
|
| 175 |
"scored_task_count": 20,
|
| 176 |
"covered_task_count": 20,
|
|
|
|
| 1 |
{
|
| 2 |
"title": "128-Episode 20-Task Radar",
|
| 3 |
"status": "pass",
|
| 4 |
+
"generated_at_utc": "2026-06-21T20:35:16+00:00",
|
| 5 |
"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.",
|
| 6 |
"task_count": 20,
|
| 7 |
"method_count": 7,
|
|
|
|
| 11 |
"higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
|
| 12 |
"lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
|
| 13 |
"raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
|
| 14 |
+
"radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
|
| 15 |
"result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
|
| 16 |
+
"foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
|
| 17 |
+
"metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
|
| 18 |
+
"raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
|
| 19 |
+
},
|
| 20 |
+
"chart_design": {
|
| 21 |
+
"mode": "grouped_small_multiples",
|
| 22 |
+
"method_count": 7,
|
| 23 |
+
"reason": "This split view has 7 methods and 140 method-task records; grouped radar panels keep related methods readable while retaining the unified source matrix.",
|
| 24 |
+
"groups": [
|
| 25 |
+
{
|
| 26 |
+
"id": "metadata_128",
|
| 27 |
+
"title": "128-episode metadata/text",
|
| 28 |
+
"series_ids": [
|
| 29 |
+
"metadata128_simple",
|
| 30 |
+
"metadata128_neural_mlp"
|
| 31 |
+
]
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": "raw_128",
|
| 35 |
+
"title": "128-episode raw features",
|
| 36 |
+
"series_ids": [
|
| 37 |
+
"raw128_simple",
|
| 38 |
+
"raw128_neural_mlp"
|
| 39 |
+
]
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"id": "foundation_models",
|
| 43 |
+
"title": "Foundation-model probes",
|
| 44 |
+
"series_ids": [
|
| 45 |
+
"qwen3_omni_v6_lora",
|
| 46 |
+
"cosmos3_super_reasoner",
|
| 47 |
+
"cosmos3_nano_future_window"
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
],
|
| 51 |
+
"visual_radius_transform": "sqrt(normalized_score)",
|
| 52 |
+
"exact_value_source": "docs/data/task_method_20_result_matrix.json"
|
| 53 |
},
|
| 54 |
"source_unified_radar": "docs/data/unified_task_model_radar.json",
|
| 55 |
"source_result_matrix": "docs/data/task_method_20_result_matrix.json",
|
|
|
|
| 63 |
"scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
|
| 64 |
"stroke_dasharray": "9 6",
|
| 65 |
"method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
|
| 66 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 67 |
"result_record_count": 20,
|
| 68 |
"scored_task_count": 20,
|
| 69 |
"covered_task_count": 20,
|
|
|
|
| 87 |
"scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
|
| 88 |
"stroke_dasharray": "3 6",
|
| 89 |
"method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
|
| 90 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 91 |
"result_record_count": 20,
|
| 92 |
"scored_task_count": 20,
|
| 93 |
"covered_task_count": 20,
|
|
|
|
| 111 |
"scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
|
| 112 |
"stroke_dasharray": "8 4",
|
| 113 |
"method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
|
| 114 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 115 |
"result_record_count": 20,
|
| 116 |
"scored_task_count": 20,
|
| 117 |
"covered_task_count": 20,
|
|
|
|
| 135 |
"scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
|
| 136 |
"stroke_dasharray": "2 5",
|
| 137 |
"method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
|
| 138 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 139 |
"result_record_count": 20,
|
| 140 |
"scored_task_count": 20,
|
| 141 |
"covered_task_count": 20,
|
|
|
|
| 159 |
"scope": "128 selected episodes, held-out test",
|
| 160 |
"stroke_dasharray": "7 7",
|
| 161 |
"method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
|
| 162 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 163 |
"result_record_count": 20,
|
| 164 |
"scored_task_count": 20,
|
| 165 |
"covered_task_count": 20,
|
|
|
|
| 182 |
"scope": "128 selected episodes, held-out test",
|
| 183 |
"stroke_dasharray": "4 7",
|
| 184 |
"method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
|
| 185 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 186 |
"result_record_count": 20,
|
| 187 |
"scored_task_count": 20,
|
| 188 |
"covered_task_count": 20,
|
|
|
|
| 205 |
"scope": "128 selected episodes, held-out test",
|
| 206 |
"stroke_dasharray": "2 7",
|
| 207 |
"method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
|
| 208 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 209 |
"result_record_count": 20,
|
| 210 |
"scored_task_count": 20,
|
| 211 |
"covered_task_count": 20,
|
data/public_surface_qa.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"title": "Ropedia Xperience-10M Public Project Surface",
|
| 3 |
"status": "pass",
|
| 4 |
-
"generated_at_utc": "2026-06-21T20:
|
| 5 |
"scope": "Repo README, GitHub Pages HTML, Hugging Face Space card, artifact dataset card, and model card.",
|
| 6 |
"checks": [
|
| 7 |
{
|
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"website_integrity": {
|
| 19 |
"exists": true,
|
| 20 |
"status": "pass",
|
| 21 |
-
"generated_at_utc": "2026-06-21T20:
|
| 22 |
},
|
| 23 |
"rendered_site_check": {
|
| 24 |
"exists": true,
|
|
@@ -28,27 +28,27 @@
|
|
| 28 |
"task_surface_integrity": {
|
| 29 |
"exists": true,
|
| 30 |
"status": "pass",
|
| 31 |
-
"generated_at_utc": "2026-06-
|
| 32 |
},
|
| 33 |
"source_alignment": {
|
| 34 |
"exists": true,
|
| 35 |
"status": "pass",
|
| 36 |
-
"generated_at_utc": "2026-06-
|
| 37 |
},
|
| 38 |
"scale_up_status": {
|
| 39 |
"exists": true,
|
| 40 |
"status": "pass",
|
| 41 |
-
"generated_at_utc": "2026-06-
|
| 42 |
},
|
| 43 |
"publication_package": {
|
| 44 |
"exists": true,
|
| 45 |
"status": "pass",
|
| 46 |
-
"generated_at_utc": "2026-06-
|
| 47 |
},
|
| 48 |
"mirror_parity": {
|
| 49 |
"exists": true,
|
| 50 |
"status": "pass",
|
| 51 |
-
"generated_at_utc": "2026-06-21T20:
|
| 52 |
}
|
| 53 |
},
|
| 54 |
"failures": {}
|
|
@@ -97,8 +97,8 @@
|
|
| 97 |
"marker_counts": {
|
| 98 |
"Ropedia Xperience-10M Task Suite": 22,
|
| 99 |
"Xperience-10M": 173,
|
| 100 |
-
"20-task":
|
| 101 |
-
"Qwen3-Omni":
|
| 102 |
"128-episode pilot": 1
|
| 103 |
}
|
| 104 |
},
|
|
|
|
| 1 |
{
|
| 2 |
"title": "Ropedia Xperience-10M Public Project Surface",
|
| 3 |
"status": "pass",
|
| 4 |
+
"generated_at_utc": "2026-06-21T20:35:18+00:00",
|
| 5 |
"scope": "Repo README, GitHub Pages HTML, Hugging Face Space card, artifact dataset card, and model card.",
|
| 6 |
"checks": [
|
| 7 |
{
|
|
|
|
| 18 |
"website_integrity": {
|
| 19 |
"exists": true,
|
| 20 |
"status": "pass",
|
| 21 |
+
"generated_at_utc": "2026-06-21T20:35:18+00:00"
|
| 22 |
},
|
| 23 |
"rendered_site_check": {
|
| 24 |
"exists": true,
|
|
|
|
| 28 |
"task_surface_integrity": {
|
| 29 |
"exists": true,
|
| 30 |
"status": "pass",
|
| 31 |
+
"generated_at_utc": "2026-06-21T20:30:48+00:00"
|
| 32 |
},
|
| 33 |
"source_alignment": {
|
| 34 |
"exists": true,
|
| 35 |
"status": "pass",
|
| 36 |
+
"generated_at_utc": "2026-06-21T20:30:47+00:00"
|
| 37 |
},
|
| 38 |
"scale_up_status": {
|
| 39 |
"exists": true,
|
| 40 |
"status": "pass",
|
| 41 |
+
"generated_at_utc": "2026-06-21T20:30:47+00:00"
|
| 42 |
},
|
| 43 |
"publication_package": {
|
| 44 |
"exists": true,
|
| 45 |
"status": "pass",
|
| 46 |
+
"generated_at_utc": "2026-06-21T20:32:45+00:00"
|
| 47 |
},
|
| 48 |
"mirror_parity": {
|
| 49 |
"exists": true,
|
| 50 |
"status": "pass",
|
| 51 |
+
"generated_at_utc": "2026-06-21T20:33:57+00:00"
|
| 52 |
}
|
| 53 |
},
|
| 54 |
"failures": {}
|
|
|
|
| 97 |
"marker_counts": {
|
| 98 |
"Ropedia Xperience-10M Task Suite": 22,
|
| 99 |
"Xperience-10M": 173,
|
| 100 |
+
"20-task": 107,
|
| 101 |
+
"Qwen3-Omni": 239,
|
| 102 |
"128-episode pilot": 1
|
| 103 |
}
|
| 104 |
},
|
data/quality_gates.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"title": "Ropedia Xperience-10M Release Checks",
|
| 3 |
"status": "pass",
|
| 4 |
-
"generated_at_utc": "2026-06-
|
| 5 |
"rule": "A release is current when the automated reports pass and the live GitHub/Hugging Face mirrors are verified after publishing.",
|
| 6 |
"automated_gates": [
|
| 7 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"title": "Ropedia Xperience-10M Release Checks",
|
| 3 |
"status": "pass",
|
| 4 |
+
"generated_at_utc": "2026-06-21T20:35:18+00:00",
|
| 5 |
"rule": "A release is current when the automated reports pass and the live GitHub/Hugging Face mirrors are verified after publishing.",
|
| 6 |
"automated_gates": [
|
| 7 |
{
|
data/scope_claims_audit.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"status": "pass",
|
| 3 |
-
"generated_at_utc": "2026-06-
|
| 4 |
"summary": {
|
| 5 |
"qwen3_omni_verified_diagnostic_pilot": true,
|
| 6 |
"dataset_manifest_num_episodes": 119,
|
|
|
|
| 1 |
{
|
| 2 |
"status": "pass",
|
| 3 |
+
"generated_at_utc": "2026-06-21T20:35:22+00:00",
|
| 4 |
"summary": {
|
| 5 |
"qwen3_omni_verified_diagnostic_pilot": true,
|
| 6 |
"dataset_manifest_num_episodes": 119,
|
data/single_episode_task_model_radar.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"title": "Single-Episode 20-Task Radar",
|
| 3 |
"status": "pass",
|
| 4 |
-
"generated_at_utc": "2026-06-
|
| 5 |
"description": "Minimal and Neural MLP baselines on the one public sample episode, both scored on all 20 task contracts.",
|
| 6 |
"task_count": 20,
|
| 7 |
"method_count": 2,
|
|
@@ -11,10 +11,28 @@
|
|
| 11 |
"higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
|
| 12 |
"lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
|
| 13 |
"raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
|
|
|
|
| 14 |
"result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
|
| 15 |
-
"foundation_model_overlay": "Qwen3-Omni and Cosmos3
|
| 16 |
-
"metadata_128_overlay": "128-episode aligned baselines
|
| 17 |
-
"raw_128_overlay": "128-episode raw-feature baselines
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
},
|
| 19 |
"source_unified_radar": "docs/data/unified_task_model_radar.json",
|
| 20 |
"source_result_matrix": "docs/data/task_method_20_result_matrix.json",
|
|
@@ -28,7 +46,7 @@
|
|
| 28 |
"scope": "1 public sample episode",
|
| 29 |
"stroke_dasharray": null,
|
| 30 |
"method_detail": "Single-episode simple heads over the public sample split.",
|
| 31 |
-
"plotted_as": "
|
| 32 |
"result_record_count": 20,
|
| 33 |
"scored_task_count": 20,
|
| 34 |
"covered_task_count": 20,
|
|
@@ -51,7 +69,7 @@
|
|
| 51 |
"scope": "1 public sample episode",
|
| 52 |
"stroke_dasharray": null,
|
| 53 |
"method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
|
| 54 |
-
"plotted_as": "
|
| 55 |
"result_record_count": 20,
|
| 56 |
"scored_task_count": 20,
|
| 57 |
"covered_task_count": 20,
|
|
|
|
| 1 |
{
|
| 2 |
"title": "Single-Episode 20-Task Radar",
|
| 3 |
"status": "pass",
|
| 4 |
+
"generated_at_utc": "2026-06-21T20:35:16+00:00",
|
| 5 |
"description": "Minimal and Neural MLP baselines on the one public sample episode, both scored on all 20 task contracts.",
|
| 6 |
"task_count": 20,
|
| 7 |
"method_count": 2,
|
|
|
|
| 11 |
"higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]",
|
| 12 |
"lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task",
|
| 13 |
"raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table",
|
| 14 |
+
"radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values",
|
| 15 |
"result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used",
|
| 16 |
+
"foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.",
|
| 17 |
+
"metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.",
|
| 18 |
+
"raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export."
|
| 19 |
+
},
|
| 20 |
+
"chart_design": {
|
| 21 |
+
"mode": "grouped_small_multiples",
|
| 22 |
+
"method_count": 2,
|
| 23 |
+
"reason": "This split view has 2 methods and 40 method-task records; grouped radar panels keep related methods readable while retaining the unified source matrix.",
|
| 24 |
+
"groups": [
|
| 25 |
+
{
|
| 26 |
+
"id": "single_episode",
|
| 27 |
+
"title": "Single-episode sample",
|
| 28 |
+
"series_ids": [
|
| 29 |
+
"minimal",
|
| 30 |
+
"neural_mlp"
|
| 31 |
+
]
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"visual_radius_transform": "sqrt(normalized_score)",
|
| 35 |
+
"exact_value_source": "docs/data/task_method_20_result_matrix.json"
|
| 36 |
},
|
| 37 |
"source_unified_radar": "docs/data/unified_task_model_radar.json",
|
| 38 |
"source_result_matrix": "docs/data/task_method_20_result_matrix.json",
|
|
|
|
| 46 |
"scope": "1 public sample episode",
|
| 47 |
"stroke_dasharray": null,
|
| 48 |
"method_detail": "Single-episode simple heads over the public sample split.",
|
| 49 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 50 |
"result_record_count": 20,
|
| 51 |
"scored_task_count": 20,
|
| 52 |
"covered_task_count": 20,
|
|
|
|
| 69 |
"scope": "1 public sample episode",
|
| 70 |
"stroke_dasharray": null,
|
| 71 |
"method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
|
| 72 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 73 |
"result_record_count": 20,
|
| 74 |
"scored_task_count": 20,
|
| 75 |
"covered_task_count": 20,
|
data/source_alignment_audit.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"title": "Ropedia Xperience-10M Source Alignment Note",
|
| 3 |
"status": "pass",
|
| 4 |
-
"generated_at_utc": "2026-06-
|
| 5 |
"alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
|
| 6 |
"alignment_summary": {
|
| 7 |
"full_dataset_repo": "ropedia-ai/xperience-10m",
|
|
|
|
| 1 |
{
|
| 2 |
"title": "Ropedia Xperience-10M Source Alignment Note",
|
| 3 |
"status": "pass",
|
| 4 |
+
"generated_at_utc": "2026-06-21T20:35:22+00:00",
|
| 5 |
"alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
|
| 6 |
"alignment_summary": {
|
| 7 |
"full_dataset_repo": "ropedia-ai/xperience-10m",
|
data/task_method_20_result_matrix.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"title": "Task Method 20-Result Matrix",
|
| 3 |
"status": "pass",
|
| 4 |
-
"generated_at_utc": "2026-06-
|
| 5 |
"task_count": 20,
|
| 6 |
"method_count": 9,
|
| 7 |
"method_task_record_count": 180,
|
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"scope": "1 public sample episode",
|
| 17 |
"stroke_dasharray": null,
|
| 18 |
"method_detail": "Single-episode simple heads over the public sample split.",
|
| 19 |
-
"plotted_as": "
|
| 20 |
"result_record_count": 20,
|
| 21 |
"scored_task_count": 20,
|
| 22 |
"covered_task_count": 20,
|
|
@@ -39,7 +39,7 @@
|
|
| 39 |
"scope": "1 public sample episode",
|
| 40 |
"stroke_dasharray": null,
|
| 41 |
"method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
|
| 42 |
-
"plotted_as": "
|
| 43 |
"result_record_count": 20,
|
| 44 |
"scored_task_count": 20,
|
| 45 |
"covered_task_count": 20,
|
|
@@ -62,7 +62,7 @@
|
|
| 62 |
"scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
|
| 63 |
"stroke_dasharray": "9 6",
|
| 64 |
"method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
|
| 65 |
-
"plotted_as": "
|
| 66 |
"result_record_count": 20,
|
| 67 |
"scored_task_count": 20,
|
| 68 |
"covered_task_count": 20,
|
|
@@ -86,7 +86,7 @@
|
|
| 86 |
"scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
|
| 87 |
"stroke_dasharray": "3 6",
|
| 88 |
"method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
|
| 89 |
-
"plotted_as": "
|
| 90 |
"result_record_count": 20,
|
| 91 |
"scored_task_count": 20,
|
| 92 |
"covered_task_count": 20,
|
|
@@ -110,7 +110,7 @@
|
|
| 110 |
"scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
|
| 111 |
"stroke_dasharray": "8 4",
|
| 112 |
"method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
|
| 113 |
-
"plotted_as": "
|
| 114 |
"result_record_count": 20,
|
| 115 |
"scored_task_count": 20,
|
| 116 |
"covered_task_count": 20,
|
|
@@ -134,7 +134,7 @@
|
|
| 134 |
"scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
|
| 135 |
"stroke_dasharray": "2 5",
|
| 136 |
"method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
|
| 137 |
-
"plotted_as": "
|
| 138 |
"result_record_count": 20,
|
| 139 |
"scored_task_count": 20,
|
| 140 |
"covered_task_count": 20,
|
|
@@ -158,7 +158,7 @@
|
|
| 158 |
"scope": "128 selected episodes, held-out test",
|
| 159 |
"stroke_dasharray": "7 7",
|
| 160 |
"method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
|
| 161 |
-
"plotted_as": "
|
| 162 |
"result_record_count": 20,
|
| 163 |
"scored_task_count": 20,
|
| 164 |
"covered_task_count": 20,
|
|
@@ -181,7 +181,7 @@
|
|
| 181 |
"scope": "128 selected episodes, held-out test",
|
| 182 |
"stroke_dasharray": "4 7",
|
| 183 |
"method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
|
| 184 |
-
"plotted_as": "
|
| 185 |
"result_record_count": 20,
|
| 186 |
"scored_task_count": 20,
|
| 187 |
"covered_task_count": 20,
|
|
@@ -204,7 +204,7 @@
|
|
| 204 |
"scope": "128 selected episodes, held-out test",
|
| 205 |
"stroke_dasharray": "2 7",
|
| 206 |
"method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
|
| 207 |
-
"plotted_as": "
|
| 208 |
"result_record_count": 20,
|
| 209 |
"scored_task_count": 20,
|
| 210 |
"covered_task_count": 20,
|
|
|
|
| 1 |
{
|
| 2 |
"title": "Task Method 20-Result Matrix",
|
| 3 |
"status": "pass",
|
| 4 |
+
"generated_at_utc": "2026-06-21T20:35:16+00:00",
|
| 5 |
"task_count": 20,
|
| 6 |
"method_count": 9,
|
| 7 |
"method_task_record_count": 180,
|
|
|
|
| 16 |
"scope": "1 public sample episode",
|
| 17 |
"stroke_dasharray": null,
|
| 18 |
"method_detail": "Single-episode simple heads over the public sample split.",
|
| 19 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 20 |
"result_record_count": 20,
|
| 21 |
"scored_task_count": 20,
|
| 22 |
"covered_task_count": 20,
|
|
|
|
| 39 |
"scope": "1 public sample episode",
|
| 40 |
"stroke_dasharray": null,
|
| 41 |
"method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
|
| 42 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 43 |
"result_record_count": 20,
|
| 44 |
"scored_task_count": 20,
|
| 45 |
"covered_task_count": 20,
|
|
|
|
| 62 |
"scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
|
| 63 |
"stroke_dasharray": "9 6",
|
| 64 |
"method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
|
| 65 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 66 |
"result_record_count": 20,
|
| 67 |
"scored_task_count": 20,
|
| 68 |
"covered_task_count": 20,
|
|
|
|
| 86 |
"scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
|
| 87 |
"stroke_dasharray": "3 6",
|
| 88 |
"method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
|
| 89 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 90 |
"result_record_count": 20,
|
| 91 |
"scored_task_count": 20,
|
| 92 |
"covered_task_count": 20,
|
|
|
|
| 110 |
"scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
|
| 111 |
"stroke_dasharray": "8 4",
|
| 112 |
"method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
|
| 113 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 114 |
"result_record_count": 20,
|
| 115 |
"scored_task_count": 20,
|
| 116 |
"covered_task_count": 20,
|
|
|
|
| 134 |
"scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
|
| 135 |
"stroke_dasharray": "2 5",
|
| 136 |
"method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
|
| 137 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 138 |
"result_record_count": 20,
|
| 139 |
"scored_task_count": 20,
|
| 140 |
"covered_task_count": 20,
|
|
|
|
| 158 |
"scope": "128 selected episodes, held-out test",
|
| 159 |
"stroke_dasharray": "7 7",
|
| 160 |
"method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
|
| 161 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 162 |
"result_record_count": 20,
|
| 163 |
"scored_task_count": 20,
|
| 164 |
"covered_task_count": 20,
|
|
|
|
| 181 |
"scope": "128 selected episodes, held-out test",
|
| 182 |
"stroke_dasharray": "4 7",
|
| 183 |
"method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
|
| 184 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 185 |
"result_record_count": 20,
|
| 186 |
"scored_task_count": 20,
|
| 187 |
"covered_task_count": 20,
|
|
|
|
| 204 |
"scope": "128 selected episodes, held-out test",
|
| 205 |
"stroke_dasharray": "2 7",
|
| 206 |
"method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
|
| 207 |
+
"plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges",
|
| 208 |
"result_record_count": 20,
|
| 209 |
"scored_task_count": 20,
|
| 210 |
"covered_task_count": 20,
|
data/task_surface_integrity.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"status": "pass",
|
| 3 |
-
"generated_at_utc": "2026-06-
|
| 4 |
"summary": {
|
| 5 |
"original_walkthrough_task_count": 12,
|
| 6 |
"expected_original_walkthrough_task_count": 12,
|
|
|
|
| 1 |
{
|
| 2 |
"status": "pass",
|
| 3 |
+
"generated_at_utc": "2026-06-21T20:35:22+00:00",
|
| 4 |
"summary": {
|
| 5 |
"original_walkthrough_task_count": 12,
|
| 6 |
"expected_original_walkthrough_task_count": 12,
|
data/website_integrity.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"status": "pass",
|
| 3 |
-
"generated_at_utc": "2026-06-21T20:
|
| 4 |
"docs_root": "docs",
|
| 5 |
"site_base": "/ropedia-xperience-10m-task-suite/",
|
| 6 |
"summary": {
|
|
@@ -80,8 +80,8 @@
|
|
| 80 |
"name": "project_overview_precedes_progress_ledger",
|
| 81 |
"status": "pass",
|
| 82 |
"reason": "The project overview should appear before the deeper progress ledger.",
|
| 83 |
-
"overview_index":
|
| 84 |
-
"evidence_index":
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"name": "project_status_links_json",
|
|
@@ -159,9 +159,9 @@
|
|
| 159 |
"name": "evaluation_protocol_between_overview_and_progress",
|
| 160 |
"status": "pass",
|
| 161 |
"reason": "The evaluation protocol should appear before the deeper evidence ledger.",
|
| 162 |
-
"overview_index":
|
| 163 |
-
"protocol_index":
|
| 164 |
-
"evidence_index":
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"name": "evaluation_protocol_links_json",
|
|
@@ -187,7 +187,7 @@
|
|
| 187 |
"status": "pass",
|
| 188 |
"reason": "The Suite anchor should show the task-suite map before the radar/results surface.",
|
| 189 |
"first_marker_index": 468,
|
| 190 |
-
"second_marker_index":
|
| 191 |
},
|
| 192 |
{
|
| 193 |
"name": "raw_sample_stream_ledger_contains_seven_modalities",
|
|
@@ -315,7 +315,7 @@
|
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"path": "data/artifact_index.json",
|
| 318 |
-
"bytes":
|
| 319 |
"top_level_type": "dict"
|
| 320 |
},
|
| 321 |
{
|
|
@@ -330,7 +330,7 @@
|
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"path": "data/episode128_task_model_radar.json",
|
| 333 |
-
"bytes":
|
| 334 |
"top_level_type": "dict"
|
| 335 |
},
|
| 336 |
{
|
|
@@ -345,7 +345,7 @@
|
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"path": "data/figure_index.json",
|
| 348 |
-
"bytes":
|
| 349 |
"top_level_type": "dict"
|
| 350 |
},
|
| 351 |
{
|
|
@@ -495,7 +495,7 @@
|
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"path": "data/single_episode_task_model_radar.json",
|
| 498 |
-
"bytes":
|
| 499 |
"top_level_type": "dict"
|
| 500 |
},
|
| 501 |
{
|
|
@@ -515,7 +515,7 @@
|
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"path": "data/task_method_20_result_matrix.json",
|
| 518 |
-
"bytes":
|
| 519 |
"top_level_type": "dict"
|
| 520 |
},
|
| 521 |
{
|
|
@@ -565,7 +565,7 @@
|
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"path": "data/unified_task_model_radar.json",
|
| 568 |
-
"bytes":
|
| 569 |
"top_level_type": "dict"
|
| 570 |
},
|
| 571 |
{
|
|
@@ -610,7 +610,7 @@
|
|
| 610 |
{
|
| 611 |
"path": "assets/charts/episode128_task_model_radar.svg",
|
| 612 |
"exists": true,
|
| 613 |
-
"bytes":
|
| 614 |
"format": "SVG",
|
| 615 |
"has_viewbox": true
|
| 616 |
},
|
|
@@ -666,7 +666,7 @@
|
|
| 666 |
{
|
| 667 |
"path": "assets/charts/single_episode_task_model_radar.svg",
|
| 668 |
"exists": true,
|
| 669 |
-
"bytes":
|
| 670 |
"format": "SVG",
|
| 671 |
"has_viewbox": true
|
| 672 |
},
|
|
@@ -680,7 +680,7 @@
|
|
| 680 |
{
|
| 681 |
"path": "assets/charts/unified_task_model_radar.svg",
|
| 682 |
"exists": true,
|
| 683 |
-
"bytes":
|
| 684 |
"format": "SVG",
|
| 685 |
"has_viewbox": true
|
| 686 |
},
|
|
|
|
| 1 |
{
|
| 2 |
"status": "pass",
|
| 3 |
+
"generated_at_utc": "2026-06-21T20:35:18+00:00",
|
| 4 |
"docs_root": "docs",
|
| 5 |
"site_base": "/ropedia-xperience-10m-task-suite/",
|
| 6 |
"summary": {
|
|
|
|
| 80 |
"name": "project_overview_precedes_progress_ledger",
|
| 81 |
"status": "pass",
|
| 82 |
"reason": "The project overview should appear before the deeper progress ledger.",
|
| 83 |
+
"overview_index": 136346,
|
| 84 |
+
"evidence_index": 187681
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"name": "project_status_links_json",
|
|
|
|
| 159 |
"name": "evaluation_protocol_between_overview_and_progress",
|
| 160 |
"status": "pass",
|
| 161 |
"reason": "The evaluation protocol should appear before the deeper evidence ledger.",
|
| 162 |
+
"overview_index": 136346,
|
| 163 |
+
"protocol_index": 183869,
|
| 164 |
+
"evidence_index": 187681
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"name": "evaluation_protocol_links_json",
|
|
|
|
| 187 |
"status": "pass",
|
| 188 |
"reason": "The Suite anchor should show the task-suite map before the radar/results surface.",
|
| 189 |
"first_marker_index": 468,
|
| 190 |
+
"second_marker_index": 2000
|
| 191 |
},
|
| 192 |
{
|
| 193 |
"name": "raw_sample_stream_ledger_contains_seven_modalities",
|
|
|
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"path": "data/artifact_index.json",
|
| 318 |
+
"bytes": 124471,
|
| 319 |
"top_level_type": "dict"
|
| 320 |
},
|
| 321 |
{
|
|
|
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"path": "data/episode128_task_model_radar.json",
|
| 333 |
+
"bytes": 186828,
|
| 334 |
"top_level_type": "dict"
|
| 335 |
},
|
| 336 |
{
|
|
|
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"path": "data/figure_index.json",
|
| 348 |
+
"bytes": 19526,
|
| 349 |
"top_level_type": "dict"
|
| 350 |
},
|
| 351 |
{
|
|
|
|
| 495 |
},
|
| 496 |
{
|
| 497 |
"path": "data/single_episode_task_model_radar.json",
|
| 498 |
+
"bytes": 52256,
|
| 499 |
"top_level_type": "dict"
|
| 500 |
},
|
| 501 |
{
|
|
|
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"path": "data/task_method_20_result_matrix.json",
|
| 518 |
+
"bytes": 128991,
|
| 519 |
"top_level_type": "dict"
|
| 520 |
},
|
| 521 |
{
|
|
|
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"path": "data/unified_task_model_radar.json",
|
| 568 |
+
"bytes": 230938,
|
| 569 |
"top_level_type": "dict"
|
| 570 |
},
|
| 571 |
{
|
|
|
|
| 610 |
{
|
| 611 |
"path": "assets/charts/episode128_task_model_radar.svg",
|
| 612 |
"exists": true,
|
| 613 |
+
"bytes": 79370,
|
| 614 |
"format": "SVG",
|
| 615 |
"has_viewbox": true
|
| 616 |
},
|
|
|
|
| 666 |
{
|
| 667 |
"path": "assets/charts/single_episode_task_model_radar.svg",
|
| 668 |
"exists": true,
|
| 669 |
+
"bytes": 36930,
|
| 670 |
"format": "SVG",
|
| 671 |
"has_viewbox": true
|
| 672 |
},
|
|
|
|
| 680 |
{
|
| 681 |
"path": "assets/charts/unified_task_model_radar.svg",
|
| 682 |
"exists": true,
|
| 683 |
+
"bytes": 98527,
|
| 684 |
"format": "SVG",
|
| 685 |
"has_viewbox": true
|
| 686 |
},
|