Add files using upload-large-folder tool

PROJECT_STATUS.md

@@ -37,7 +37,7 @@ The current no-new-episode enhancement layer records how to push the selected
 | Public package policy | Verified | `DATA_NOTICE.md`, `REPRODUCIBILITY.md` | Raw Xperience-10M data, private gated files, large archives, credentials, and full Qwen weights are not redistributed. |
 | Reproducibility | Verified for the public sample | `REPRODUCIBILITY.md`, `docs/data/reproducibility_matrix.json`, `notes/reproducibility_audit.md` | The public sample workflow has explicit commands, expected outputs, and exact-match reproduction evidence. |
 | 128-episode aligned baselines | Verified companion result | `results/omni_finetune/multi_episode_128_task_baselines/BASELINE_ALIGNMENT_REPORT.md`, `results/omni_finetune/multi_episode_128_task_baselines/summary_report.json`, `scripts/omni/run_128_task_baselines.py` | The earlier simple and neural baseline framing is aligned to the same selected 96/16/16 episode split used by the Qwen3-Omni pilot. JSON-supported tasks have metadata/text simple and neural MLP metrics; raw-feature-only tasks are explicitly marked unsupported until 128-run sensor feature blocks are available. |
-| Qwen3-Omni fine-tuning | Final verified diagnostic held-out result; JSON target met | `docs/data/omni_finetune_verified_result.json`, `results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_structured_json_v4_4epoch_full8gpu_lora_eval_test_full/`, `scripts/omni/package_verified_omni_result.py`, `scripts/omni/audit_verified_omni_package.py`, `scripts/omni/analyze_qwen3_omni_errors.py` | The selected 96/16/16 episode split produced a current public-safe v4 four-epoch held-out package with 3,808 exported windows, 512 validation windows, 448 test predictions, validation/audit summaries, and the public LoRA adapter. JSON validity is 100.00%, meeting the 98% target; transition accuracy is 97.32%, contact accuracy is 72.99%, object micro-F1 is 31.10%, next-action accuracy is 3.35%, and action/subtask metrics remain weak, so it is still a diagnostic baseline rather than a strong model-quality claim. |
+| Qwen3-Omni fine-tuning | Latest v6 diagnostic branch verified; JSON target met | `docs/data/omni_finetune_verified_result.json`, `docs/data/qwen3_v5_v6_comparison.json`, `results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md`, `results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/`, `scripts/omni/package_verified_omni_result.py`, `scripts/omni/audit_verified_omni_package.py`, `scripts/omni/analyze_qwen3_omni_errors.py` | The selected 96/16/16 episode split now has a current public-safe v6 rank64/lr5e-5 held-out package with 34,269 exported windows and 4,032 test predictions. JSON validity is 99.90%, meeting the 98% target; transition accuracy is 98.98%, contact accuracy is 81.77%, object micro-F1 is 30.65%, next-action accuracy is 4.31%, and action/subtask metrics remain weak. v6 improves action macro-F1 and contact accuracy versus v5, but v5 remains stronger on JSON validity, subtask, next-action, transition, and object metrics. |
 | Raw Xperience-10M redistribution | Not included | `DATA_NOTICE.md`, `docs/data/publication_audit.json` | Raw MP4, HDF5, RRD files, private gated data, and full Qwen weights are intentionally excluded. |
 
 ## Fast Research Route
@@ -79,10 +79,11 @@ The current no-new-episode enhancement layer records how to push the selected
   current results use one public sample episode.
 - Public-facing fine-tuning results should come from the verified result
   package, not from live process logs or setup-only artifacts.
-- The final Qwen3-Omni v4 held-out package verifies the pipeline and meets the
-  strict-JSON target, but not strong action/subtask model quality: JSON
-  validity is 100.00%, action macro-F1 is 0.0019, and subtask accuracy is
-  0.0000.
+- The latest Qwen3-Omni v6 held-out package verifies the current dense
+  multiscale branch and meets the strict-JSON target, but not strong
+  action/subtask model quality: JSON validity is 99.90%, action macro-F1 is
+  0.0029, and subtask accuracy is 0.0037. v5 remains the pinned prior release
+  row because it is still stronger on several metrics.
 - The current 128-episode task suite can be pushed further without more raw
   episodes by using dense/multiscale windows, hierarchical action/subtask
   targets, stronger label-normalized scoring, and compact raw-feature shards

RESEARCH_ROADMAP.md

@@ -11,7 +11,7 @@ should exist before the stage is treated as complete.
 | --- | --- | --- | --- | --- |
 | Public-Sample Task Lab | Implemented | One public Xperience-10M sample episode is available. | 1,161 aligned windows, 12 task contracts, minimal heads, neural MLP heads, modality atlas, task walkthroughs, and derived figures. | `PROJECT_STATUS.md`, `EVALUATION_PROTOCOL.md`, `RESEARCH_TAKEAWAYS.md`, `docs/data/summary_metrics.json`, `results/episode_task_suite/summary_report.json` |
 | Multi-Episode Data Preparation | Implemented for first selected pilot | Gated dataset availability and enough storage for selected episodes. | 128 selected episodes, episode manifest, missing-view manifest, held-out episode split, and source-discovery report. | `results/omni_finetune/DATA_ACCESS_STATUS.md`, `results/omni_finetune/MULTI_EPISODE_ACCESS_STATUS.md`, `results/omni_finetune/xperience10m_128_episode_selection.json` |
-| Qwen3-Omni LoRA Final Diagnostic Result | Verified baseline | Selected episodes prepared locally with no train/test episode leakage. | Dataset JSONL/media manifests, LoRA adapter checkpoint, progress logs, validation monitoring, held-out predictions, metrics, confusion matrices, run report, and public LoRA adapter repo. | `docs/data/omni_finetune_verified_result.json`, `results/omni_finetune/verified_public/`, `metrics.json`, `predictions.jsonl`, `RUN_REPORT.md`, `https://huggingface.co/cy0307/ropedia-qwen3-omni-lora-128ep` |
+| Qwen3-Omni LoRA Latest Diagnostic Branch | Verified latest branch | Selected episodes prepared locally with no train/test episode leakage. | Dataset JSONL/media manifests, LoRA adapter checkpoint, progress logs, validation monitoring, held-out predictions, metrics, confusion matrices, v5/v6 comparison, run report, and public LoRA adapter repo. | `docs/data/omni_finetune_verified_result.json`, `docs/data/qwen3_v5_v6_comparison.json`, `results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md`, `results/omni_finetune/verified_public/`, `metrics.json`, `predictions.jsonl`, `RUN_REPORT.md`, `https://huggingface.co/cy0307/ropedia-qwen3-omni-lora-128ep` |
 | 128-Episode Same-Split Simple/NN Baselines | Verified companion result | Derived Qwen JSONL export for the selected 96/16/16 split. | Same 12 task ids, simple metadata/text baselines, neural MLP baselines where JSON labels support them, and explicit unsupported markers for tasks that still require raw 128 feature blocks. | `results/omni_finetune/multi_episode_128_task_baselines/BASELINE_ALIGNMENT_REPORT.md`, `summary_report.json`, `scripts/omni/run_128_task_baselines.py` |
 | 128-Episode Task Suite Enhancement Pack | Current no-new-episode plan | Same selected 96/16/16 split and current public 3,808-window export. | Dense-window and multiscale export estimates, hierarchical action/subtask target contract, raw-feature shard priorities for unsupported tasks, Qwen v5 and Cosmos continuation run cards, and publication-ready artifacts. | `TASK_SUITE_ENHANCEMENT_128.md`, `docs/data/task_suite_enhancement_128.json`, `results/omni_finetune/task_suite_enhancement_128_v1_20260608/enhancement_plan.json`, `scripts/omni/build_task_suite_enhancement_128.py` |
 | Action/Subtask Error-Analysis Pass | Active next step | The final diagnostic package meets strict JSON validity but has weak action/subtask held-out quality. | Same 96/16/16 split, action/subtask confusion analysis, unseen-label analysis, object/action family breakdowns, and comparison to the final verified Qwen baseline. | Updated error-analysis tables, held-out metrics by failure type, and verified public package. |
@@ -24,8 +24,8 @@ should exist before the stage is treated as complete.
 
 The useful next decision is model-quality improvement plus backbone fit without
 requiring more raw episodes first: keep the public-sample task suite as the
-development harness, use the verified Qwen3-Omni final diagnostic result as the
-first cross-episode baseline, then improve action/subtask quality before
+development harness, use the verified Qwen3-Omni v6 diagnostic branch plus the
+pinned v5 row as the current cross-episode references, then improve action/subtask quality before
 claiming model quality. The earlier simple and neural baseline framing is now
 aligned to the same 96/16/16 split through metadata/text baselines for
 JSON-supported task ids; raw-feature-only tasks remain marked as needing the

metrics/artifact_index.json

@@ -1,13 +1,13 @@
 {
   "title": "Ropedia Xperience-10M Task Suite Artifact Index",
-  "generated_at_utc": "2026-06-12T18:14:49+00:00",
+  "generated_at_utc": "2026-06-13T17:46:38+00:00",
   "status": "pass",
-  "artifact_count": 159,
+  "artifact_count": 162,
   "missing": [],
   "by_kind": {
     "project_path": 14,
     "scaleup_contract": 7,
-    "scaleup_status": 36,
+    "scaleup_status": 38,
     "publication_workflow": 5,
     "project_scope": 1,
     "source_alignment": 5,
@@ -32,7 +32,7 @@
     "citation": 1,
     "license": 1,
     "verified_public_package": 10,
-    "publication_audit": 6
+    "publication_audit": 7
   },
   "artifacts": [
     {
@@ -65,8 +65,8 @@
       "surface": "repo_hf",
       "shows": "Gives a compact current-state table for first-pass readers.",
       "exists": true,
-      "bytes": 13535,
-      "sha256": "595f90e26d75baba46a0827eb2ec38d0c6badb137437f642dff4e88e22b7ca80"
+      "bytes": 13755,
+      "sha256": "342897ae05ceab83d626765c0052c140e414ba25ebda4fce9fb07bb37a2decef"
     },
     {
       "id": "project_status_json",
@@ -76,8 +76,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable copy of the current project status for website and HF mirrors.",
       "exists": true,
-      "bytes": 23198,
-      "sha256": "07678354fde90a7e15134f5deff036eb200f7bf422ab2350ff64825b902843d5"
+      "bytes": 23535,
+      "sha256": "9ffae32ff0b3750f89179d2ce92205f95a5b53069d0aa344d6342c23b1efebbd"
     },
     {
       "id": "research_roadmap",
@@ -87,8 +87,8 @@
       "surface": "repo_hf",
       "shows": "Defines the path from public-sample task development to multi-episode held-out evaluation and larger omni-model extensions.",
       "exists": true,
-      "bytes": 14354,
-      "sha256": "7d385916e6d07cfa5f95e80b501fe58237f671711691cc8c792479d233991ef5"
+      "bytes": 14503,
+      "sha256": "bb06fb0ccf336cafb0305883b7f93c2e1af547c9ff04b1fa6fc87481d54bcf61"
     },
     {
       "id": "research_roadmap_json",
@@ -98,8 +98,8 @@
       "surface": "website_hf",
       "shows": "Machine-readable research roadmap for the website and Hugging Face mirrors.",
       "exists": true,
-      "bytes": 13313,
-      "sha256": "719a8b5f45810d6b09788391d8549eb5226e480454c9f2a4ed7380ceacfd834b"
+      "bytes": 13450,
+      "sha256": "668220626950f8e55410b8f829dba6306d0b2feedafdf0198800ad9814992d84"
     },
     {
       "id": "foundation_model_plan",
@@ -264,7 +264,7 @@
       "shows": "Summarizes the 2026-06-09 full-parameter FSDP feasibility gates: 1/8/32/64-step guarded runs passed, the 128-step opportunistic pilot was preempted for Qwen v5 handoff, and no full checkpoints or weights are published.",
       "exists": true,
       "bytes": 3253,
-      "sha256": "5c0e49adad861e00bede7f9245808e6e68346e7bc51c0b0142d2b99f944f2408"
+      "sha256": "b25f1d8cde814207b4c3234bf07140cf99a0ede29af3f53dbc146aab464e8a9b"
     },
     {
       "id": "qwen3_full_parameter_gates_json",
@@ -275,7 +275,29 @@
       "shows": "Machine-readable summary of full-parameter feasibility evidence and publication policy for website and Hugging Face mirrors.",
       "exists": true,
       "bytes": 12183,
-      "sha256": "50b8b93f0bae34c7fa269ae52d7c2073d6122fdafc9297f380c052d94253bf3f"
+      "sha256": "d051608d3428645778f721e538af93566ab772871a825ac12825dd5f18e94a95"
+    },
+    {
+      "id": "qwen3_v5_v6_comparison",
+      "title": "Qwen3-Omni v5/v6 comparison",
+      "path": "results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md",
+      "kind": "scaleup_status",
+      "surface": "repo_hf",
+      "shows": "Reader-facing comparison of the verified Qwen3 v5 release row and the latest verified v6 row, including metric deltas and release-tag policy.",
+      "exists": true,
+      "bytes": 1793,
+      "sha256": "890430b05ace20375fc9534f923d170c0509037272ba4ef523e3ca2f3c9ac746"
+    },
+    {
+      "id": "qwen3_v5_v6_comparison_json",
+      "title": "Qwen3-Omni v5/v6 comparison JSON",
+      "path": "docs/data/qwen3_v5_v6_comparison.json",
+      "kind": "scaleup_status",
+      "surface": "website_hf",
+      "shows": "Machine-readable v5/v6 metric deltas and publication recommendation for website and Hugging Face mirrors.",
+      "exists": true,
+      "bytes": 2814,
+      "sha256": "f5d16e279a82cdc6266a1318584bf38cbc0b105296d437f9b8bf0398403aace5"
     },
     {
       "id": "qwen3_full_parameter_gates_builder",
@@ -362,8 +384,8 @@
       "surface": "website_hf",
       "shows": "Gives a short project path with scope status and public surfaces.",
       "exists": true,
-      "bytes": 10496,
-      "sha256": "fc21325035c3b8d4892bfad50dd1a7f5f562a662b7da7be73f7349cb515544ef"
+      "bytes": 10597,
+      "sha256": "a64b7c033c54879e0183e7ec794d3197fb483024c25947759287fcd4b7e0fec1"
     },
     {
       "id": "artifact_guide",
@@ -418,7 +440,7 @@
       "shows": "Machine-readable source-alignment pass/fail check for repo, website, and HF surfaces.",
       "exists": true,
       "bytes": 4432,
-      "sha256": "d5ada9ec76cace484a779672d636222f1dfa281135508ff1b5d5eac98908bf60"
+      "sha256": "0d0d381f726c1e3787fb3fb15b6fb8879512c26fa0dc06fb943e1a239b0063dd"
     },
     {
       "id": "source_alignment_validator",
@@ -671,7 +693,7 @@
       "shows": "Machine-readable release-check summary for validators, mirrors, and public project surfaces.",
       "exists": true,
       "bytes": 8097,
-      "sha256": "9b4783b42d0a6f58f2bc36bb7990c86dc85af9d346cb59c90dca402e2c4cf0de"
+      "sha256": "1cdc8b4767b3ca88eada654a3117aa2de253fea7af62573b080088e8f1b311bd"
     },
     {
       "id": "public_surface_qa",
@@ -785,8 +807,8 @@
       "surface": "repo",
       "shows": "Fetches the published GitHub/HF URLs and compares live hashes and public-card markers against the release assets.",
       "exists": true,
-      "bytes": 42224,
-      "sha256": "069b05229b72b9fa0c0917afd18655f58e5258499b43889dd96a87f29f577890"
+      "bytes": 42394,
+      "sha256": "43a70436108eea3fa6692096ebf318fb755ff040d925094ef9de018f212fde18"
     },
     {
       "id": "reproducibility_contract",
@@ -818,8 +840,8 @@
       "surface": "repo_hf",
       "shows": "Generates the selective artifact catalog from local files.",
       "exists": true,
-      "bytes": 42045,
-      "sha256": "0954119cda59bb9c77cba362a206ac237eae73c4a1dc44cfa56599f170fc94de"
+      "bytes": 42809,
+      "sha256": "c03d1b1367ad191fea0be3c634fddf8ee6fdc2118bf17396920c16cc288c4ef0"
     },
     {
       "id": "publication_audit",
@@ -842,7 +864,7 @@
       "volatile": true,
       "shows": "Separates setup paths from completed held-out-episode results.",
       "exists": true,
-      "bytes": 21325,
+      "bytes": 21795,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -866,7 +888,7 @@
       "volatile": true,
       "shows": "Confirms local website links, anchors, JSON data files, and referenced images resolve.",
       "exists": true,
-      "bytes": 15654,
+      "bytes": 15774,
       "hash_policy": "existence_and_size_only"
     },
     {
@@ -899,8 +921,8 @@
       "surface": "website_hf",
       "shows": "Mirrors task metrics for the static dashboard.",
       "exists": true,
-      "bytes": 27604,
-      "sha256": "ebaf9d598b4cd91118f149cafa01fe4d17629499565b7be0c7ce4a0ffcd70f6b"
+      "bytes": 27807,
+      "sha256": "3a6a5ee59562ae189844cb4ba26d6e261c2f73a8e54bb6e2fbc3e307c2d123fa"
     },
     {
       "id": "feature_manifest",
@@ -1119,8 +1141,8 @@
       "surface": "repo_hf",
       "shows": "Reader-facing comparison of the single-episode task suite, 128-episode aligned baselines, Qwen3-Omni packages, and Cosmos3 future-window branch.",
       "exists": true,
-      "bytes": 15731,
-      "sha256": "1ee5621a825219c1125a9c3f3ac779ac8bfa2fc45668531dbee3a728be13bfb5"
+      "bytes": 15999,
+      "sha256": "d5a7118a878b202adbc50e3436bbe134e5de139f2a9e97176efe9ecc0f446088"
     },
     {
       "id": "omni_model_comparison_json",
@@ -1130,8 +1152,8 @@
       "surface": "repo_hf",
       "shows": "Machine-readable comparison of the current result versions, per-task aligned baselines, verified Qwen3 packages, and Cosmos3 package.",
       "exists": true,
-      "bytes": 81593,
-      "sha256": "c570f0810dec46f9a14969089245051c2b3a255f074bd9d06f529615fa6fbd73"
+      "bytes": 81866,
+      "sha256": "191125098a66ecccfa27395c0f9776616f74b4bf8fb19f16b75cda7ed06cb4b2"
     },
     {
       "id": "cosmos3_nano_verified_summary",
@@ -1548,8 +1570,8 @@
       "surface": "repo_hf",
       "shows": "Public-safe verified package for xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full (qwen3_omni_lora, status=verified).",
       "exists": true,
-      "file_count": 13,
-      "bytes": 12189099
+      "file_count": 14,
+      "bytes": 12189730
     },
     {
       "id": "verified_public_summary_xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full",
@@ -1595,6 +1617,17 @@
       "bytes": 49205,
       "sha256": "fc198c3e443877bca42cc33bec6e2a194d6cb20e97c28e931a90736c45538bba"
     },
+    {
+      "id": "verified_public_package_audit_xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full",
+      "title": "Verified package audit: Qwen3-Omni LoRA",
+      "path": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/package_audit.json",
+      "kind": "publication_audit",
+      "surface": "repo_hf",
+      "shows": "Package audit for xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full.",
+      "exists": true,
+      "bytes": 631,
+      "sha256": "7cf478ae33c52bae0ba742e81da8e482e06d0853eecd85f895f447a708f81718"
+    },
     {
       "id": "verified_public_package_xperience10m_qwen3_omni_128ep_structured_json_v2_reuse_full8gpu_lora_eval_test_full",
       "title": "Verified public package: Qwen3-Omni LoRA",

metrics/mirror_parity.json

@@ -1,9 +1,9 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-12T18:14:59+00:00",
+  "generated_at_utc": "2026-06-13T17:47:14+00:00",
   "hf_root": "hf_publish",
   "summary": {
-    "group_count": 363,
+    "group_count": 366,
     "failure_count": 0,
     "failures_by_surface": {}
   },
@@ -138,45 +138,45 @@
       "local": {
         "path": "repo:docs/data/artifact_index.json",
         "exists": true,
-        "bytes": 87230,
-        "sha256": "7426cbf2be990a353dd2f6a289b887aa37b12cb6ee4716de37a16709deb26715"
+        "bytes": 88913,
+        "sha256": "ad08fe33d7563a5be1a92158fb6e86c28ca990d6009cbef62d8c0bb616cf5ff6"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/artifact_index.json",
           "exists": true,
-          "bytes": 87230,
-          "sha256": "7426cbf2be990a353dd2f6a289b887aa37b12cb6ee4716de37a16709deb26715"
+          "bytes": 88913,
+          "sha256": "ad08fe33d7563a5be1a92158fb6e86c28ca990d6009cbef62d8c0bb616cf5ff6"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/artifact_index.json",
           "exists": true,
-          "bytes": 87230,
-          "sha256": "7426cbf2be990a353dd2f6a289b887aa37b12cb6ee4716de37a16709deb26715"
+          "bytes": 88913,
+          "sha256": "ad08fe33d7563a5be1a92158fb6e86c28ca990d6009cbef62d8c0bb616cf5ff6"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 87230,
-          "sha256": "7426cbf2be990a353dd2f6a289b887aa37b12cb6ee4716de37a16709deb26715"
+          "bytes": 88913,
+          "sha256": "ad08fe33d7563a5be1a92158fb6e86c28ca990d6009cbef62d8c0bb616cf5ff6"
         },
         "hf_model_data": {
           "path": "hf_model:data/artifact_index.json",
           "exists": true,
-          "bytes": 87230,
-          "sha256": "7426cbf2be990a353dd2f6a289b887aa37b12cb6ee4716de37a16709deb26715"
+          "bytes": 88913,
+          "sha256": "ad08fe33d7563a5be1a92158fb6e86c28ca990d6009cbef62d8c0bb616cf5ff6"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/artifact_index.json",
           "exists": true,
-          "bytes": 87230,
-          "sha256": "7426cbf2be990a353dd2f6a289b887aa37b12cb6ee4716de37a16709deb26715"
+          "bytes": 88913,
+          "sha256": "ad08fe33d7563a5be1a92158fb6e86c28ca990d6009cbef62d8c0bb616cf5ff6"
         },
         "hf_model": {
           "path": "hf_model:metrics/artifact_index.json",
           "exists": true,
-          "bytes": 87230,
-          "sha256": "7426cbf2be990a353dd2f6a289b887aa37b12cb6ee4716de37a16709deb26715"
+          "bytes": 88913,
+          "sha256": "ad08fe33d7563a5be1a92158fb6e86c28ca990d6009cbef62d8c0bb616cf5ff6"
         }
       },
       "failures": []
@@ -530,45 +530,45 @@
       "local": {
         "path": "repo:docs/data/omni_finetune_verified_result.json",
         "exists": true,
-        "bytes": 4431,
-        "sha256": "cc51c2d7be5e924e7c8fd4847e548d29097e403b24aafbb387a1ca59a505b099"
+        "bytes": 4325,
+        "sha256": "861d451551143d28759a9e475abc88868148c5184bb23821d9a1584cad0a195f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/omni_finetune_verified_result.json",
           "exists": true,
-          "bytes": 4431,
-          "sha256": "cc51c2d7be5e924e7c8fd4847e548d29097e403b24aafbb387a1ca59a505b099"
+          "bytes": 4325,
+          "sha256": "861d451551143d28759a9e475abc88868148c5184bb23821d9a1584cad0a195f"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/omni_finetune_verified_result.json",
           "exists": true,
-          "bytes": 4431,
-          "sha256": "cc51c2d7be5e924e7c8fd4847e548d29097e403b24aafbb387a1ca59a505b099"
+          "bytes": 4325,
+          "sha256": "861d451551143d28759a9e475abc88868148c5184bb23821d9a1584cad0a195f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/omni_finetune_verified_result.json",
           "exists": true,
-          "bytes": 4431,
-          "sha256": "cc51c2d7be5e924e7c8fd4847e548d29097e403b24aafbb387a1ca59a505b099"
+          "bytes": 4325,
+          "sha256": "861d451551143d28759a9e475abc88868148c5184bb23821d9a1584cad0a195f"
         },
         "hf_model_data": {
           "path": "hf_model:data/omni_finetune_verified_result.json",
           "exists": true,
-          "bytes": 4431,
-          "sha256": "cc51c2d7be5e924e7c8fd4847e548d29097e403b24aafbb387a1ca59a505b099"
+          "bytes": 4325,
+          "sha256": "861d451551143d28759a9e475abc88868148c5184bb23821d9a1584cad0a195f"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/omni_finetune_verified_result.json",
           "exists": true,
-          "bytes": 4431,
-          "sha256": "cc51c2d7be5e924e7c8fd4847e548d29097e403b24aafbb387a1ca59a505b099"
+          "bytes": 4325,
+          "sha256": "861d451551143d28759a9e475abc88868148c5184bb23821d9a1584cad0a195f"
         },
         "hf_model": {
           "path": "hf_model:metrics/omni_finetune_verified_result.json",
           "exists": true,
-          "bytes": 4431,
-          "sha256": "cc51c2d7be5e924e7c8fd4847e548d29097e403b24aafbb387a1ca59a505b099"
+          "bytes": 4325,
+          "sha256": "861d451551143d28759a9e475abc88868148c5184bb23821d9a1584cad0a195f"
         }
       },
       "failures": []
@@ -579,45 +579,45 @@
       "local": {
         "path": "repo:docs/data/omni_model_comparison.json",
         "exists": true,
-        "bytes": 81593,
-        "sha256": "c570f0810dec46f9a14969089245051c2b3a255f074bd9d06f529615fa6fbd73"
+        "bytes": 81866,
+        "sha256": "191125098a66ecccfa27395c0f9776616f74b4bf8fb19f16b75cda7ed06cb4b2"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/omni_model_comparison.json",
           "exists": true,
-          "bytes": 81593,
-          "sha256": "c570f0810dec46f9a14969089245051c2b3a255f074bd9d06f529615fa6fbd73"
+          "bytes": 81866,
+          "sha256": "191125098a66ecccfa27395c0f9776616f74b4bf8fb19f16b75cda7ed06cb4b2"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/omni_model_comparison.json",
           "exists": true,
-          "bytes": 81593,
-          "sha256": "c570f0810dec46f9a14969089245051c2b3a255f074bd9d06f529615fa6fbd73"
+          "bytes": 81866,
+          "sha256": "191125098a66ecccfa27395c0f9776616f74b4bf8fb19f16b75cda7ed06cb4b2"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/omni_model_comparison.json",
           "exists": true,
-          "bytes": 81593,
-          "sha256": "c570f0810dec46f9a14969089245051c2b3a255f074bd9d06f529615fa6fbd73"
+          "bytes": 81866,
+          "sha256": "191125098a66ecccfa27395c0f9776616f74b4bf8fb19f16b75cda7ed06cb4b2"
         },
         "hf_model_data": {
           "path": "hf_model:data/omni_model_comparison.json",
           "exists": true,
-          "bytes": 81593,
-          "sha256": "c570f0810dec46f9a14969089245051c2b3a255f074bd9d06f529615fa6fbd73"
+          "bytes": 81866,
+          "sha256": "191125098a66ecccfa27395c0f9776616f74b4bf8fb19f16b75cda7ed06cb4b2"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/omni_model_comparison.json",
           "exists": true,
-          "bytes": 81593,
-          "sha256": "c570f0810dec46f9a14969089245051c2b3a255f074bd9d06f529615fa6fbd73"
+          "bytes": 81866,
+          "sha256": "191125098a66ecccfa27395c0f9776616f74b4bf8fb19f16b75cda7ed06cb4b2"
         },
         "hf_model": {
           "path": "hf_model:metrics/omni_model_comparison.json",
           "exists": true,
-          "bytes": 81593,
-          "sha256": "c570f0810dec46f9a14969089245051c2b3a255f074bd9d06f529615fa6fbd73"
+          "bytes": 81866,
+          "sha256": "191125098a66ecccfa27395c0f9776616f74b4bf8fb19f16b75cda7ed06cb4b2"
         }
       },
       "failures": []
@@ -726,45 +726,45 @@
       "local": {
         "path": "repo:docs/data/project_packet.json",
         "exists": true,
-        "bytes": 10496,
-        "sha256": "fc21325035c3b8d4892bfad50dd1a7f5f562a662b7da7be73f7349cb515544ef"
+        "bytes": 10597,
+        "sha256": "a64b7c033c54879e0183e7ec794d3197fb483024c25947759287fcd4b7e0fec1"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/project_packet.json",
           "exists": true,
-          "bytes": 10496,
-          "sha256": "fc21325035c3b8d4892bfad50dd1a7f5f562a662b7da7be73f7349cb515544ef"
+          "bytes": 10597,
+          "sha256": "a64b7c033c54879e0183e7ec794d3197fb483024c25947759287fcd4b7e0fec1"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/project_packet.json",
           "exists": true,
-          "bytes": 10496,
-          "sha256": "fc21325035c3b8d4892bfad50dd1a7f5f562a662b7da7be73f7349cb515544ef"
+          "bytes": 10597,
+          "sha256": "a64b7c033c54879e0183e7ec794d3197fb483024c25947759287fcd4b7e0fec1"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/project_packet.json",
           "exists": true,
-          "bytes": 10496,
-          "sha256": "fc21325035c3b8d4892bfad50dd1a7f5f562a662b7da7be73f7349cb515544ef"
+          "bytes": 10597,
+          "sha256": "a64b7c033c54879e0183e7ec794d3197fb483024c25947759287fcd4b7e0fec1"
         },
         "hf_model_data": {
           "path": "hf_model:data/project_packet.json",
           "exists": true,
-          "bytes": 10496,
-          "sha256": "fc21325035c3b8d4892bfad50dd1a7f5f562a662b7da7be73f7349cb515544ef"
+          "bytes": 10597,
+          "sha256": "a64b7c033c54879e0183e7ec794d3197fb483024c25947759287fcd4b7e0fec1"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/project_packet.json",
           "exists": true,
-          "bytes": 10496,
-          "sha256": "fc21325035c3b8d4892bfad50dd1a7f5f562a662b7da7be73f7349cb515544ef"
+          "bytes": 10597,
+          "sha256": "a64b7c033c54879e0183e7ec794d3197fb483024c25947759287fcd4b7e0fec1"
         },
         "hf_model": {
           "path": "hf_model:metrics/project_packet.json",
           "exists": true,
-          "bytes": 10496,
-          "sha256": "fc21325035c3b8d4892bfad50dd1a7f5f562a662b7da7be73f7349cb515544ef"
+          "bytes": 10597,
+          "sha256": "a64b7c033c54879e0183e7ec794d3197fb483024c25947759287fcd4b7e0fec1"
         }
       },
       "failures": []
@@ -775,45 +775,45 @@
       "local": {
         "path": "repo:docs/data/project_status.json",
         "exists": true,
-        "bytes": 23198,
-        "sha256": "07678354fde90a7e15134f5deff036eb200f7bf422ab2350ff64825b902843d5"
+        "bytes": 23535,
+        "sha256": "9ffae32ff0b3750f89179d2ce92205f95a5b53069d0aa344d6342c23b1efebbd"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/project_status.json",
           "exists": true,
-          "bytes": 23198,
-          "sha256": "07678354fde90a7e15134f5deff036eb200f7bf422ab2350ff64825b902843d5"
+          "bytes": 23535,
+          "sha256": "9ffae32ff0b3750f89179d2ce92205f95a5b53069d0aa344d6342c23b1efebbd"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/project_status.json",
           "exists": true,
-          "bytes": 23198,
-          "sha256": "07678354fde90a7e15134f5deff036eb200f7bf422ab2350ff64825b902843d5"
+          "bytes": 23535,
+          "sha256": "9ffae32ff0b3750f89179d2ce92205f95a5b53069d0aa344d6342c23b1efebbd"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/project_status.json",
           "exists": true,
-          "bytes": 23198,
-          "sha256": "07678354fde90a7e15134f5deff036eb200f7bf422ab2350ff64825b902843d5"
+          "bytes": 23535,
+          "sha256": "9ffae32ff0b3750f89179d2ce92205f95a5b53069d0aa344d6342c23b1efebbd"
         },
         "hf_model_data": {
           "path": "hf_model:data/project_status.json",
           "exists": true,
-          "bytes": 23198,
-          "sha256": "07678354fde90a7e15134f5deff036eb200f7bf422ab2350ff64825b902843d5"
+          "bytes": 23535,
+          "sha256": "9ffae32ff0b3750f89179d2ce92205f95a5b53069d0aa344d6342c23b1efebbd"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/project_status.json",
           "exists": true,
-          "bytes": 23198,
-          "sha256": "07678354fde90a7e15134f5deff036eb200f7bf422ab2350ff64825b902843d5"
+          "bytes": 23535,
+          "sha256": "9ffae32ff0b3750f89179d2ce92205f95a5b53069d0aa344d6342c23b1efebbd"
         },
         "hf_model": {
           "path": "hf_model:metrics/project_status.json",
           "exists": true,
-          "bytes": 23198,
-          "sha256": "07678354fde90a7e15134f5deff036eb200f7bf422ab2350ff64825b902843d5"
+          "bytes": 23535,
+          "sha256": "9ffae32ff0b3750f89179d2ce92205f95a5b53069d0aa344d6342c23b1efebbd"
         }
       },
       "failures": []
@@ -825,44 +825,44 @@
         "path": "repo:docs/data/publication_audit.json",
         "exists": true,
         "bytes": 7591,
-        "sha256": "5e7e31a14197a95c2411225ccda07dbcd257747d8c809627ed119993bf409033"
+        "sha256": "5670d3c1f7592d96a342d4b6cd2f2cedfbe29ac309db282f2082fc2414f4469a"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/publication_audit.json",
           "exists": true,
           "bytes": 7591,
-          "sha256": "5e7e31a14197a95c2411225ccda07dbcd257747d8c809627ed119993bf409033"
+          "sha256": "5670d3c1f7592d96a342d4b6cd2f2cedfbe29ac309db282f2082fc2414f4469a"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/publication_audit.json",
           "exists": true,
           "bytes": 7591,
-          "sha256": "5e7e31a14197a95c2411225ccda07dbcd257747d8c809627ed119993bf409033"
+          "sha256": "5670d3c1f7592d96a342d4b6cd2f2cedfbe29ac309db282f2082fc2414f4469a"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 7591,
-          "sha256": "5e7e31a14197a95c2411225ccda07dbcd257747d8c809627ed119993bf409033"
+          "sha256": "5670d3c1f7592d96a342d4b6cd2f2cedfbe29ac309db282f2082fc2414f4469a"
         },
         "hf_model_data": {
           "path": "hf_model:data/publication_audit.json",
           "exists": true,
           "bytes": 7591,
-          "sha256": "5e7e31a14197a95c2411225ccda07dbcd257747d8c809627ed119993bf409033"
+          "sha256": "5670d3c1f7592d96a342d4b6cd2f2cedfbe29ac309db282f2082fc2414f4469a"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/publication_audit.json",
           "exists": true,
           "bytes": 7591,
-          "sha256": "5e7e31a14197a95c2411225ccda07dbcd257747d8c809627ed119993bf409033"
+          "sha256": "5670d3c1f7592d96a342d4b6cd2f2cedfbe29ac309db282f2082fc2414f4469a"
         },
         "hf_model": {
           "path": "hf_model:metrics/publication_audit.json",
           "exists": true,
           "bytes": 7591,
-          "sha256": "5e7e31a14197a95c2411225ccda07dbcd257747d8c809627ed119993bf409033"
+          "sha256": "5670d3c1f7592d96a342d4b6cd2f2cedfbe29ac309db282f2082fc2414f4469a"
         }
       },
       "failures": []
@@ -874,44 +874,44 @@
         "path": "repo:docs/data/public_surface_qa.json",
         "exists": true,
         "bytes": 5640,
-        "sha256": "1054926dee80548a2a10db93766ffc1d2578bc326136af2ab4afbed54af8334e"
+        "sha256": "e4557f23f199b87063d8a97aca64253d58bed5be3538a51526ac86ce3258ee7c"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/public_surface_qa.json",
           "exists": true,
           "bytes": 5640,
-          "sha256": "1054926dee80548a2a10db93766ffc1d2578bc326136af2ab4afbed54af8334e"
+          "sha256": "e4557f23f199b87063d8a97aca64253d58bed5be3538a51526ac86ce3258ee7c"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/public_surface_qa.json",
           "exists": true,
           "bytes": 5640,
-          "sha256": "1054926dee80548a2a10db93766ffc1d2578bc326136af2ab4afbed54af8334e"
+          "sha256": "e4557f23f199b87063d8a97aca64253d58bed5be3538a51526ac86ce3258ee7c"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 5640,
-          "sha256": "1054926dee80548a2a10db93766ffc1d2578bc326136af2ab4afbed54af8334e"
+          "sha256": "e4557f23f199b87063d8a97aca64253d58bed5be3538a51526ac86ce3258ee7c"
         },
         "hf_model_data": {
           "path": "hf_model:data/public_surface_qa.json",
           "exists": true,
           "bytes": 5640,
-          "sha256": "1054926dee80548a2a10db93766ffc1d2578bc326136af2ab4afbed54af8334e"
+          "sha256": "e4557f23f199b87063d8a97aca64253d58bed5be3538a51526ac86ce3258ee7c"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/public_surface_qa.json",
           "exists": true,
           "bytes": 5640,
-          "sha256": "1054926dee80548a2a10db93766ffc1d2578bc326136af2ab4afbed54af8334e"
+          "sha256": "e4557f23f199b87063d8a97aca64253d58bed5be3538a51526ac86ce3258ee7c"
         },
         "hf_model": {
           "path": "hf_model:metrics/public_surface_qa.json",
           "exists": true,
           "bytes": 5640,
-          "sha256": "1054926dee80548a2a10db93766ffc1d2578bc326136af2ab4afbed54af8334e"
+          "sha256": "e4557f23f199b87063d8a97aca64253d58bed5be3538a51526ac86ce3258ee7c"
         }
       },
       "failures": []
@@ -923,44 +923,93 @@
         "path": "repo:docs/data/qwen3_full_parameter_gates.json",
         "exists": true,
         "bytes": 12183,
-        "sha256": "50b8b93f0bae34c7fa269ae52d7c2073d6122fdafc9297f380c052d94253bf3f"
+        "sha256": "d051608d3428645778f721e538af93566ab772871a825ac12825dd5f18e94a95"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/qwen3_full_parameter_gates.json",
           "exists": true,
           "bytes": 12183,
-          "sha256": "50b8b93f0bae34c7fa269ae52d7c2073d6122fdafc9297f380c052d94253bf3f"
+          "sha256": "d051608d3428645778f721e538af93566ab772871a825ac12825dd5f18e94a95"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/qwen3_full_parameter_gates.json",
           "exists": true,
           "bytes": 12183,
-          "sha256": "50b8b93f0bae34c7fa269ae52d7c2073d6122fdafc9297f380c052d94253bf3f"
+          "sha256": "d051608d3428645778f721e538af93566ab772871a825ac12825dd5f18e94a95"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/qwen3_full_parameter_gates.json",
           "exists": true,
           "bytes": 12183,
-          "sha256": "50b8b93f0bae34c7fa269ae52d7c2073d6122fdafc9297f380c052d94253bf3f"
+          "sha256": "d051608d3428645778f721e538af93566ab772871a825ac12825dd5f18e94a95"
         },
         "hf_model_data": {
           "path": "hf_model:data/qwen3_full_parameter_gates.json",
           "exists": true,
           "bytes": 12183,
-          "sha256": "50b8b93f0bae34c7fa269ae52d7c2073d6122fdafc9297f380c052d94253bf3f"
+          "sha256": "d051608d3428645778f721e538af93566ab772871a825ac12825dd5f18e94a95"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/qwen3_full_parameter_gates.json",
           "exists": true,
           "bytes": 12183,
-          "sha256": "50b8b93f0bae34c7fa269ae52d7c2073d6122fdafc9297f380c052d94253bf3f"
+          "sha256": "d051608d3428645778f721e538af93566ab772871a825ac12825dd5f18e94a95"
         },
         "hf_model": {
           "path": "hf_model:metrics/qwen3_full_parameter_gates.json",
           "exists": true,
           "bytes": 12183,
-          "sha256": "50b8b93f0bae34c7fa269ae52d7c2073d6122fdafc9297f380c052d94253bf3f"
+          "sha256": "d051608d3428645778f721e538af93566ab772871a825ac12825dd5f18e94a95"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "data/qwen3_v5_v6_comparison.json",
+      "status": "pass",
+      "local": {
+        "path": "repo:docs/data/qwen3_v5_v6_comparison.json",
+        "exists": true,
+        "bytes": 2814,
+        "sha256": "f5d16e279a82cdc6266a1318584bf38cbc0b105296d437f9b8bf0398403aace5"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:data/qwen3_v5_v6_comparison.json",
+          "exists": true,
+          "bytes": 2814,
+          "sha256": "f5d16e279a82cdc6266a1318584bf38cbc0b105296d437f9b8bf0398403aace5"
+        },
+        "hf_artifacts_data": {
+          "path": "hf_artifacts:data/qwen3_v5_v6_comparison.json",
+          "exists": true,
+          "bytes": 2814,
+          "sha256": "f5d16e279a82cdc6266a1318584bf38cbc0b105296d437f9b8bf0398403aace5"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:docs/data/qwen3_v5_v6_comparison.json",
+          "exists": true,
+          "bytes": 2814,
+          "sha256": "f5d16e279a82cdc6266a1318584bf38cbc0b105296d437f9b8bf0398403aace5"
+        },
+        "hf_model_data": {
+          "path": "hf_model:data/qwen3_v5_v6_comparison.json",
+          "exists": true,
+          "bytes": 2814,
+          "sha256": "f5d16e279a82cdc6266a1318584bf38cbc0b105296d437f9b8bf0398403aace5"
+        },
+        "hf_model_docs_data": {
+          "path": "hf_model:docs/data/qwen3_v5_v6_comparison.json",
+          "exists": true,
+          "bytes": 2814,
+          "sha256": "f5d16e279a82cdc6266a1318584bf38cbc0b105296d437f9b8bf0398403aace5"
+        },
+        "hf_model": {
+          "path": "hf_model:metrics/qwen3_v5_v6_comparison.json",
+          "exists": true,
+          "bytes": 2814,
+          "sha256": "f5d16e279a82cdc6266a1318584bf38cbc0b105296d437f9b8bf0398403aace5"
         }
       },
       "failures": []
@@ -972,44 +1021,44 @@
         "path": "repo:docs/data/quality_gates.json",
         "exists": true,
         "bytes": 8097,
-        "sha256": "9780a5415c71ae68b708c65e8d194b2601f66eef20c8bd3def2fd01763dc8e55"
+        "sha256": "1cdc8b4767b3ca88eada654a3117aa2de253fea7af62573b080088e8f1b311bd"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/quality_gates.json",
           "exists": true,
           "bytes": 8097,
-          "sha256": "9780a5415c71ae68b708c65e8d194b2601f66eef20c8bd3def2fd01763dc8e55"
+          "sha256": "1cdc8b4767b3ca88eada654a3117aa2de253fea7af62573b080088e8f1b311bd"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/quality_gates.json",
           "exists": true,
           "bytes": 8097,
-          "sha256": "9780a5415c71ae68b708c65e8d194b2601f66eef20c8bd3def2fd01763dc8e55"
+          "sha256": "1cdc8b4767b3ca88eada654a3117aa2de253fea7af62573b080088e8f1b311bd"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8097,
-          "sha256": "9780a5415c71ae68b708c65e8d194b2601f66eef20c8bd3def2fd01763dc8e55"
+          "sha256": "1cdc8b4767b3ca88eada654a3117aa2de253fea7af62573b080088e8f1b311bd"
         },
         "hf_model_data": {
           "path": "hf_model:data/quality_gates.json",
           "exists": true,
           "bytes": 8097,
-          "sha256": "9780a5415c71ae68b708c65e8d194b2601f66eef20c8bd3def2fd01763dc8e55"
+          "sha256": "1cdc8b4767b3ca88eada654a3117aa2de253fea7af62573b080088e8f1b311bd"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/quality_gates.json",
           "exists": true,
           "bytes": 8097,
-          "sha256": "9780a5415c71ae68b708c65e8d194b2601f66eef20c8bd3def2fd01763dc8e55"
+          "sha256": "1cdc8b4767b3ca88eada654a3117aa2de253fea7af62573b080088e8f1b311bd"
         },
         "hf_model": {
           "path": "hf_model:metrics/quality_gates.json",
           "exists": true,
           "bytes": 8097,
-          "sha256": "9780a5415c71ae68b708c65e8d194b2601f66eef20c8bd3def2fd01763dc8e55"
+          "sha256": "1cdc8b4767b3ca88eada654a3117aa2de253fea7af62573b080088e8f1b311bd"
         }
       },
       "failures": []
@@ -1118,45 +1167,45 @@
       "local": {
         "path": "repo:docs/data/research_roadmap.json",
         "exists": true,
-        "bytes": 13313,
-        "sha256": "719a8b5f45810d6b09788391d8549eb5226e480454c9f2a4ed7380ceacfd834b"
+        "bytes": 13450,
+        "sha256": "668220626950f8e55410b8f829dba6306d0b2feedafdf0198800ad9814992d84"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/research_roadmap.json",
           "exists": true,
-          "bytes": 13313,
-          "sha256": "719a8b5f45810d6b09788391d8549eb5226e480454c9f2a4ed7380ceacfd834b"
+          "bytes": 13450,
+          "sha256": "668220626950f8e55410b8f829dba6306d0b2feedafdf0198800ad9814992d84"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/research_roadmap.json",
           "exists": true,
-          "bytes": 13313,
-          "sha256": "719a8b5f45810d6b09788391d8549eb5226e480454c9f2a4ed7380ceacfd834b"
+          "bytes": 13450,
+          "sha256": "668220626950f8e55410b8f829dba6306d0b2feedafdf0198800ad9814992d84"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/research_roadmap.json",
           "exists": true,
-          "bytes": 13313,
-          "sha256": "719a8b5f45810d6b09788391d8549eb5226e480454c9f2a4ed7380ceacfd834b"
+          "bytes": 13450,
+          "sha256": "668220626950f8e55410b8f829dba6306d0b2feedafdf0198800ad9814992d84"
         },
         "hf_model_data": {
           "path": "hf_model:data/research_roadmap.json",
           "exists": true,
-          "bytes": 13313,
-          "sha256": "719a8b5f45810d6b09788391d8549eb5226e480454c9f2a4ed7380ceacfd834b"
+          "bytes": 13450,
+          "sha256": "668220626950f8e55410b8f829dba6306d0b2feedafdf0198800ad9814992d84"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/research_roadmap.json",
           "exists": true,
-          "bytes": 13313,
-          "sha256": "719a8b5f45810d6b09788391d8549eb5226e480454c9f2a4ed7380ceacfd834b"
+          "bytes": 13450,
+          "sha256": "668220626950f8e55410b8f829dba6306d0b2feedafdf0198800ad9814992d84"
         },
         "hf_model": {
           "path": "hf_model:metrics/research_roadmap.json",
           "exists": true,
-          "bytes": 13313,
-          "sha256": "719a8b5f45810d6b09788391d8549eb5226e480454c9f2a4ed7380ceacfd834b"
+          "bytes": 13450,
+          "sha256": "668220626950f8e55410b8f829dba6306d0b2feedafdf0198800ad9814992d84"
         }
       },
       "failures": []
@@ -1167,45 +1216,45 @@
       "local": {
         "path": "repo:docs/data/research_roadmap_interactive.json",
         "exists": true,
-        "bytes": 145083,
-        "sha256": "3f3896f728d65efdee792a255a878243a7f1d777f3c28aac680a6755741e8e6f"
+        "bytes": 145234,
+        "sha256": "c11a51b33e2af6b1afaf42c3cec1c38c1aed912ebbc815f466c5f085adea6f6f"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/research_roadmap_interactive.json",
           "exists": true,
-          "bytes": 145083,
-          "sha256": "3f3896f728d65efdee792a255a878243a7f1d777f3c28aac680a6755741e8e6f"
+          "bytes": 145234,
+          "sha256": "c11a51b33e2af6b1afaf42c3cec1c38c1aed912ebbc815f466c5f085adea6f6f"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/research_roadmap_interactive.json",
           "exists": true,
-          "bytes": 145083,
-          "sha256": "3f3896f728d65efdee792a255a878243a7f1d777f3c28aac680a6755741e8e6f"
+          "bytes": 145234,
+          "sha256": "c11a51b33e2af6b1afaf42c3cec1c38c1aed912ebbc815f466c5f085adea6f6f"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/research_roadmap_interactive.json",
           "exists": true,
-          "bytes": 145083,
-          "sha256": "3f3896f728d65efdee792a255a878243a7f1d777f3c28aac680a6755741e8e6f"
+          "bytes": 145234,
+          "sha256": "c11a51b33e2af6b1afaf42c3cec1c38c1aed912ebbc815f466c5f085adea6f6f"
         },
         "hf_model_data": {
           "path": "hf_model:data/research_roadmap_interactive.json",
           "exists": true,
-          "bytes": 145083,
-          "sha256": "3f3896f728d65efdee792a255a878243a7f1d777f3c28aac680a6755741e8e6f"
+          "bytes": 145234,
+          "sha256": "c11a51b33e2af6b1afaf42c3cec1c38c1aed912ebbc815f466c5f085adea6f6f"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/research_roadmap_interactive.json",
           "exists": true,
-          "bytes": 145083,
-          "sha256": "3f3896f728d65efdee792a255a878243a7f1d777f3c28aac680a6755741e8e6f"
+          "bytes": 145234,
+          "sha256": "c11a51b33e2af6b1afaf42c3cec1c38c1aed912ebbc815f466c5f085adea6f6f"
         },
         "hf_model": {
           "path": "hf_model:metrics/research_roadmap_interactive.json",
           "exists": true,
-          "bytes": 145083,
-          "sha256": "3f3896f728d65efdee792a255a878243a7f1d777f3c28aac680a6755741e8e6f"
+          "bytes": 145234,
+          "sha256": "c11a51b33e2af6b1afaf42c3cec1c38c1aed912ebbc815f466c5f085adea6f6f"
         }
       },
       "failures": []
@@ -1363,45 +1412,45 @@
       "local": {
         "path": "repo:docs/data/scope_claims_audit.json",
         "exists": true,
-        "bytes": 21325,
-        "sha256": "09bbffdae552c243e06c874b9791c2f805214fbc0e7cd4fb42c31cb756a5b374"
+        "bytes": 21795,
+        "sha256": "289f6522b8d7dd8efd98cd1fa5cf0e766710439b4caac9cd634973abfdc73846"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/scope_claims_audit.json",
           "exists": true,
-          "bytes": 21325,
-          "sha256": "09bbffdae552c243e06c874b9791c2f805214fbc0e7cd4fb42c31cb756a5b374"
+          "bytes": 21795,
+          "sha256": "289f6522b8d7dd8efd98cd1fa5cf0e766710439b4caac9cd634973abfdc73846"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/scope_claims_audit.json",
           "exists": true,
-          "bytes": 21325,
-          "sha256": "09bbffdae552c243e06c874b9791c2f805214fbc0e7cd4fb42c31cb756a5b374"
+          "bytes": 21795,
+          "sha256": "289f6522b8d7dd8efd98cd1fa5cf0e766710439b4caac9cd634973abfdc73846"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/scope_claims_audit.json",
           "exists": true,
-          "bytes": 21325,
-          "sha256": "09bbffdae552c243e06c874b9791c2f805214fbc0e7cd4fb42c31cb756a5b374"
+          "bytes": 21795,
+          "sha256": "289f6522b8d7dd8efd98cd1fa5cf0e766710439b4caac9cd634973abfdc73846"
         },
         "hf_model_data": {
           "path": "hf_model:data/scope_claims_audit.json",
           "exists": true,
-          "bytes": 21325,
-          "sha256": "09bbffdae552c243e06c874b9791c2f805214fbc0e7cd4fb42c31cb756a5b374"
+          "bytes": 21795,
+          "sha256": "289f6522b8d7dd8efd98cd1fa5cf0e766710439b4caac9cd634973abfdc73846"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/scope_claims_audit.json",
           "exists": true,
-          "bytes": 21325,
-          "sha256": "09bbffdae552c243e06c874b9791c2f805214fbc0e7cd4fb42c31cb756a5b374"
+          "bytes": 21795,
+          "sha256": "289f6522b8d7dd8efd98cd1fa5cf0e766710439b4caac9cd634973abfdc73846"
         },
         "hf_model": {
           "path": "hf_model:metrics/scope_claims_audit.json",
           "exists": true,
-          "bytes": 21325,
-          "sha256": "09bbffdae552c243e06c874b9791c2f805214fbc0e7cd4fb42c31cb756a5b374"
+          "bytes": 21795,
+          "sha256": "289f6522b8d7dd8efd98cd1fa5cf0e766710439b4caac9cd634973abfdc73846"
         }
       },
       "failures": []
@@ -1462,44 +1511,44 @@
         "path": "repo:docs/data/source_alignment_audit.json",
         "exists": true,
         "bytes": 4432,
-        "sha256": "b5c63578c8a6b24247cb5e9aca175e5004194c76c7cbbc2e510374fcb30277d8"
+        "sha256": "b277329512546c334ce68deda9d7d2c8f6e5df3e04a28b5a2fcc6fd7aa5036dd"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "b5c63578c8a6b24247cb5e9aca175e5004194c76c7cbbc2e510374fcb30277d8"
+          "sha256": "b277329512546c334ce68deda9d7d2c8f6e5df3e04a28b5a2fcc6fd7aa5036dd"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "b5c63578c8a6b24247cb5e9aca175e5004194c76c7cbbc2e510374fcb30277d8"
+          "sha256": "b277329512546c334ce68deda9d7d2c8f6e5df3e04a28b5a2fcc6fd7aa5036dd"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "b5c63578c8a6b24247cb5e9aca175e5004194c76c7cbbc2e510374fcb30277d8"
+          "sha256": "b277329512546c334ce68deda9d7d2c8f6e5df3e04a28b5a2fcc6fd7aa5036dd"
         },
         "hf_model_data": {
           "path": "hf_model:data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "b5c63578c8a6b24247cb5e9aca175e5004194c76c7cbbc2e510374fcb30277d8"
+          "sha256": "b277329512546c334ce68deda9d7d2c8f6e5df3e04a28b5a2fcc6fd7aa5036dd"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "b5c63578c8a6b24247cb5e9aca175e5004194c76c7cbbc2e510374fcb30277d8"
+          "sha256": "b277329512546c334ce68deda9d7d2c8f6e5df3e04a28b5a2fcc6fd7aa5036dd"
         },
         "hf_model": {
           "path": "hf_model:metrics/source_alignment_audit.json",
           "exists": true,
           "bytes": 4432,
-          "sha256": "b5c63578c8a6b24247cb5e9aca175e5004194c76c7cbbc2e510374fcb30277d8"
+          "sha256": "b277329512546c334ce68deda9d7d2c8f6e5df3e04a28b5a2fcc6fd7aa5036dd"
         }
       },
       "failures": []
@@ -1510,45 +1559,45 @@
       "local": {
         "path": "repo:docs/data/summary_metrics.json",
         "exists": true,
-        "bytes": 27604,
-        "sha256": "ebaf9d598b4cd91118f149cafa01fe4d17629499565b7be0c7ce4a0ffcd70f6b"
+        "bytes": 27807,
+        "sha256": "3a6a5ee59562ae189844cb4ba26d6e261c2f73a8e54bb6e2fbc3e307c2d123fa"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/summary_metrics.json",
           "exists": true,
-          "bytes": 27604,
-          "sha256": "ebaf9d598b4cd91118f149cafa01fe4d17629499565b7be0c7ce4a0ffcd70f6b"
+          "bytes": 27807,
+          "sha256": "3a6a5ee59562ae189844cb4ba26d6e261c2f73a8e54bb6e2fbc3e307c2d123fa"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/summary_metrics.json",
           "exists": true,
-          "bytes": 27604,
-          "sha256": "ebaf9d598b4cd91118f149cafa01fe4d17629499565b7be0c7ce4a0ffcd70f6b"
+          "bytes": 27807,
+          "sha256": "3a6a5ee59562ae189844cb4ba26d6e261c2f73a8e54bb6e2fbc3e307c2d123fa"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/summary_metrics.json",
           "exists": true,
-          "bytes": 27604,
-          "sha256": "ebaf9d598b4cd91118f149cafa01fe4d17629499565b7be0c7ce4a0ffcd70f6b"
+          "bytes": 27807,
+          "sha256": "3a6a5ee59562ae189844cb4ba26d6e261c2f73a8e54bb6e2fbc3e307c2d123fa"
         },
         "hf_model_data": {
           "path": "hf_model:data/summary_metrics.json",
           "exists": true,
-          "bytes": 27604,
-          "sha256": "ebaf9d598b4cd91118f149cafa01fe4d17629499565b7be0c7ce4a0ffcd70f6b"
+          "bytes": 27807,
+          "sha256": "3a6a5ee59562ae189844cb4ba26d6e261c2f73a8e54bb6e2fbc3e307c2d123fa"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/summary_metrics.json",
           "exists": true,
-          "bytes": 27604,
-          "sha256": "ebaf9d598b4cd91118f149cafa01fe4d17629499565b7be0c7ce4a0ffcd70f6b"
+          "bytes": 27807,
+          "sha256": "3a6a5ee59562ae189844cb4ba26d6e261c2f73a8e54bb6e2fbc3e307c2d123fa"
         },
         "hf_model": {
           "path": "hf_model:metrics/summary_metrics.json",
           "exists": true,
-          "bytes": 27604,
-          "sha256": "ebaf9d598b4cd91118f149cafa01fe4d17629499565b7be0c7ce4a0ffcd70f6b"
+          "bytes": 27807,
+          "sha256": "3a6a5ee59562ae189844cb4ba26d6e261c2f73a8e54bb6e2fbc3e307c2d123fa"
         }
       },
       "failures": []
@@ -1609,44 +1658,44 @@
         "path": "repo:docs/data/task_surface_integrity.json",
         "exists": true,
         "bytes": 45779,
-        "sha256": "f3078c3993b127ab63afec6973cadb7007549ff3ea5582aa7eb5bc00bcd1c17b"
+        "sha256": "71efc018d2ccb2ce4d2efc67adca9cae4e25b23b1abd96ca1cbb0ff7fc578f9b"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "f3078c3993b127ab63afec6973cadb7007549ff3ea5582aa7eb5bc00bcd1c17b"
+          "sha256": "71efc018d2ccb2ce4d2efc67adca9cae4e25b23b1abd96ca1cbb0ff7fc578f9b"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "f3078c3993b127ab63afec6973cadb7007549ff3ea5582aa7eb5bc00bcd1c17b"
+          "sha256": "71efc018d2ccb2ce4d2efc67adca9cae4e25b23b1abd96ca1cbb0ff7fc578f9b"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "f3078c3993b127ab63afec6973cadb7007549ff3ea5582aa7eb5bc00bcd1c17b"
+          "sha256": "71efc018d2ccb2ce4d2efc67adca9cae4e25b23b1abd96ca1cbb0ff7fc578f9b"
         },
         "hf_model_data": {
           "path": "hf_model:data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "f3078c3993b127ab63afec6973cadb7007549ff3ea5582aa7eb5bc00bcd1c17b"
+          "sha256": "71efc018d2ccb2ce4d2efc67adca9cae4e25b23b1abd96ca1cbb0ff7fc578f9b"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "f3078c3993b127ab63afec6973cadb7007549ff3ea5582aa7eb5bc00bcd1c17b"
+          "sha256": "71efc018d2ccb2ce4d2efc67adca9cae4e25b23b1abd96ca1cbb0ff7fc578f9b"
         },
         "hf_model": {
           "path": "hf_model:metrics/task_surface_integrity.json",
           "exists": true,
           "bytes": 45779,
-          "sha256": "f3078c3993b127ab63afec6973cadb7007549ff3ea5582aa7eb5bc00bcd1c17b"
+          "sha256": "71efc018d2ccb2ce4d2efc67adca9cae4e25b23b1abd96ca1cbb0ff7fc578f9b"
         }
       },
       "failures": []
@@ -1706,45 +1755,45 @@
       "local": {
         "path": "repo:docs/data/website_integrity.json",
         "exists": true,
-        "bytes": 15654,
-        "sha256": "b5235c9c9a9394977ec707ed5c42b50a26f4538bd499bff04861da6be45ba404"
+        "bytes": 15774,
+        "sha256": "baafcf64bfdb562f588d5f8d2c6ee1a3cb7f381de50e6f8d9400409e07cc7116"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:data/website_integrity.json",
           "exists": true,
-          "bytes": 15654,
-          "sha256": "b5235c9c9a9394977ec707ed5c42b50a26f4538bd499bff04861da6be45ba404"
+          "bytes": 15774,
+          "sha256": "baafcf64bfdb562f588d5f8d2c6ee1a3cb7f381de50e6f8d9400409e07cc7116"
         },
         "hf_artifacts_data": {
           "path": "hf_artifacts:data/website_integrity.json",
           "exists": true,
-          "bytes": 15654,
-          "sha256": "b5235c9c9a9394977ec707ed5c42b50a26f4538bd499bff04861da6be45ba404"
+          "bytes": 15774,
+          "sha256": "baafcf64bfdb562f588d5f8d2c6ee1a3cb7f381de50e6f8d9400409e07cc7116"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:docs/data/website_integrity.json",
           "exists": true,
-          "bytes": 15654,
-          "sha256": "b5235c9c9a9394977ec707ed5c42b50a26f4538bd499bff04861da6be45ba404"
+          "bytes": 15774,
+          "sha256": "baafcf64bfdb562f588d5f8d2c6ee1a3cb7f381de50e6f8d9400409e07cc7116"
         },
         "hf_model_data": {
           "path": "hf_model:data/website_integrity.json",
           "exists": true,
-          "bytes": 15654,
-          "sha256": "b5235c9c9a9394977ec707ed5c42b50a26f4538bd499bff04861da6be45ba404"
+          "bytes": 15774,
+          "sha256": "baafcf64bfdb562f588d5f8d2c6ee1a3cb7f381de50e6f8d9400409e07cc7116"
         },
         "hf_model_docs_data": {
           "path": "hf_model:docs/data/website_integrity.json",
           "exists": true,
-          "bytes": 15654,
-          "sha256": "b5235c9c9a9394977ec707ed5c42b50a26f4538bd499bff04861da6be45ba404"
+          "bytes": 15774,
+          "sha256": "baafcf64bfdb562f588d5f8d2c6ee1a3cb7f381de50e6f8d9400409e07cc7116"
         },
         "hf_model": {
           "path": "hf_model:metrics/website_integrity.json",
           "exists": true,
-          "bytes": 15654,
-          "sha256": "b5235c9c9a9394977ec707ed5c42b50a26f4538bd499bff04861da6be45ba404"
+          "bytes": 15774,
+          "sha256": "baafcf64bfdb562f588d5f8d2c6ee1a3cb7f381de50e6f8d9400409e07cc7116"
         }
       },
       "failures": []
@@ -2520,21 +2569,21 @@
       "local": {
         "path": "repo:scripts/omni/build_omni_model_comparison.py",
         "exists": true,
-        "bytes": 44466,
-        "sha256": "5e89e608edcbc69e8fbc5beb1370ccc443110fe5125d32400cb0aeafb56356aa"
+        "bytes": 45217,
+        "sha256": "14a326dbd62737ece3947b0af42685394c6018807f62f705f236dca17a5bee61"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/omni/build_omni_model_comparison.py",
           "exists": true,
-          "bytes": 44466,
-          "sha256": "5e89e608edcbc69e8fbc5beb1370ccc443110fe5125d32400cb0aeafb56356aa"
+          "bytes": 45217,
+          "sha256": "14a326dbd62737ece3947b0af42685394c6018807f62f705f236dca17a5bee61"
         },
         "hf_model": {
           "path": "hf_model:scripts/omni/build_omni_model_comparison.py",
           "exists": true,
-          "bytes": 44466,
-          "sha256": "5e89e608edcbc69e8fbc5beb1370ccc443110fe5125d32400cb0aeafb56356aa"
+          "bytes": 45217,
+          "sha256": "14a326dbd62737ece3947b0af42685394c6018807f62f705f236dca17a5bee61"
         }
       },
       "failures": []
@@ -2895,21 +2944,21 @@
       "local": {
         "path": "repo:scripts/build_artifact_index.py",
         "exists": true,
-        "bytes": 42045,
-        "sha256": "0954119cda59bb9c77cba362a206ac237eae73c4a1dc44cfa56599f170fc94de"
+        "bytes": 42809,
+        "sha256": "c03d1b1367ad191fea0be3c634fddf8ee6fdc2118bf17396920c16cc288c4ef0"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 42045,
-          "sha256": "0954119cda59bb9c77cba362a206ac237eae73c4a1dc44cfa56599f170fc94de"
+          "bytes": 42809,
+          "sha256": "c03d1b1367ad191fea0be3c634fddf8ee6fdc2118bf17396920c16cc288c4ef0"
         },
         "hf_model": {
           "path": "hf_model:scripts/build_artifact_index.py",
           "exists": true,
-          "bytes": 42045,
-          "sha256": "0954119cda59bb9c77cba362a206ac237eae73c4a1dc44cfa56599f170fc94de"
+          "bytes": 42809,
+          "sha256": "c03d1b1367ad191fea0be3c634fddf8ee6fdc2118bf17396920c16cc288c4ef0"
         }
       },
       "failures": []
@@ -3170,21 +3219,21 @@
       "local": {
         "path": "repo:scripts/verify_live_publication.py",
         "exists": true,
-        "bytes": 42224,
-        "sha256": "069b05229b72b9fa0c0917afd18655f58e5258499b43889dd96a87f29f577890"
+        "bytes": 42394,
+        "sha256": "43a70436108eea3fa6692096ebf318fb755ff040d925094ef9de018f212fde18"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/verify_live_publication.py",
           "exists": true,
-          "bytes": 42224,
-          "sha256": "069b05229b72b9fa0c0917afd18655f58e5258499b43889dd96a87f29f577890"
+          "bytes": 42394,
+          "sha256": "43a70436108eea3fa6692096ebf318fb755ff040d925094ef9de018f212fde18"
         },
         "hf_model": {
           "path": "hf_model:scripts/verify_live_publication.py",
           "exists": true,
-          "bytes": 42224,
-          "sha256": "069b05229b72b9fa0c0917afd18655f58e5258499b43889dd96a87f29f577890"
+          "bytes": 42394,
+          "sha256": "43a70436108eea3fa6692096ebf318fb755ff040d925094ef9de018f212fde18"
         }
       },
       "failures": []
@@ -3195,21 +3244,21 @@
       "local": {
         "path": "repo:scripts/validate_mirror_parity.py",
         "exists": true,
-        "bytes": 20941,
-        "sha256": "edbc633ae7482ce190a02bc956d0c0e3fda0d102e1b1448e9d15fe966442ab38"
+        "bytes": 21032,
+        "sha256": "cee8801466f5b0593e4a43258d8d8f90c4b87737bfcb966d8a72a010eae12c5b"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/validate_mirror_parity.py",
           "exists": true,
-          "bytes": 20941,
-          "sha256": "edbc633ae7482ce190a02bc956d0c0e3fda0d102e1b1448e9d15fe966442ab38"
+          "bytes": 21032,
+          "sha256": "cee8801466f5b0593e4a43258d8d8f90c4b87737bfcb966d8a72a010eae12c5b"
         },
         "hf_model": {
           "path": "hf_model:scripts/validate_mirror_parity.py",
           "exists": true,
-          "bytes": 20941,
-          "sha256": "edbc633ae7482ce190a02bc956d0c0e3fda0d102e1b1448e9d15fe966442ab38"
+          "bytes": 21032,
+          "sha256": "cee8801466f5b0593e4a43258d8d8f90c4b87737bfcb966d8a72a010eae12c5b"
         }
       },
       "failures": []
@@ -3245,21 +3294,21 @@
       "local": {
         "path": "repo:scripts/validate_scope_claims.py",
         "exists": true,
-        "bytes": 12028,
-        "sha256": "1aff00ee149f3e49e7c5043afea24311128be633ef45c27e4d5bab4f16f87bd4"
+        "bytes": 13424,
+        "sha256": "080867b4e05c97e63506625b2063ad88f841dba7327a39fc41b17dbfcaa17f92"
       },
       "mirrors": {
         "hf_artifacts": {
           "path": "hf_artifacts:scripts/validate_scope_claims.py",
           "exists": true,
-          "bytes": 12028,
-          "sha256": "1aff00ee149f3e49e7c5043afea24311128be633ef45c27e4d5bab4f16f87bd4"
+          "bytes": 13424,
+          "sha256": "080867b4e05c97e63506625b2063ad88f841dba7327a39fc41b17dbfcaa17f92"
         },
         "hf_model": {
           "path": "hf_model:scripts/validate_scope_claims.py",
           "exists": true,
-          "bytes": 12028,
-          "sha256": "1aff00ee149f3e49e7c5043afea24311128be633ef45c27e4d5bab4f16f87bd4"
+          "bytes": 13424,
+          "sha256": "080867b4e05c97e63506625b2063ad88f841dba7327a39fc41b17dbfcaa17f92"
         }
       },
       "failures": []
@@ -3445,21 +3494,21 @@
       "local": {
         "path": "repo:docs/index.html",
         "exists": true,
-        "bytes": 186490,
-        "sha256": "f0d74ebaf983f1d49643069efe505cd45a39731349af85329b89fe8cbc5b1758"
+        "bytes": 186593,
+        "sha256": "13094cd7413fb4dc5c4cdd5d6f72b45e2b4ef35bef5e36d28fa073998b1abfcb"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:index.html",
           "exists": true,
-          "bytes": 186490,
-          "sha256": "f0d74ebaf983f1d49643069efe505cd45a39731349af85329b89fe8cbc5b1758"
+          "bytes": 186593,
+          "sha256": "13094cd7413fb4dc5c4cdd5d6f72b45e2b4ef35bef5e36d28fa073998b1abfcb"
         },
         "hf_artifacts_docs": {
           "path": "hf_artifacts:docs/index.html",
           "exists": true,
-          "bytes": 186490,
-          "sha256": "f0d74ebaf983f1d49643069efe505cd45a39731349af85329b89fe8cbc5b1758"
+          "bytes": 186593,
+          "sha256": "13094cd7413fb4dc5c4cdd5d6f72b45e2b4ef35bef5e36d28fa073998b1abfcb"
         }
       },
       "failures": []
@@ -3731,27 +3780,27 @@
       "local": {
         "path": "repo:results/omni_finetune/OMNI_MODEL_COMPARISON.md",
         "exists": true,
-        "bytes": 15731,
-        "sha256": "1ee5621a825219c1125a9c3f3ac779ac8bfa2fc45668531dbee3a728be13bfb5"
+        "bytes": 15999,
+        "sha256": "d5a7118a878b202adbc50e3436bbe134e5de139f2a9e97176efe9ecc0f446088"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:results/omni_finetune/OMNI_MODEL_COMPARISON.md",
           "exists": true,
-          "bytes": 15731,
-          "sha256": "1ee5621a825219c1125a9c3f3ac779ac8bfa2fc45668531dbee3a728be13bfb5"
+          "bytes": 15999,
+          "sha256": "d5a7118a878b202adbc50e3436bbe134e5de139f2a9e97176efe9ecc0f446088"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:results/omni_finetune/OMNI_MODEL_COMPARISON.md",
           "exists": true,
-          "bytes": 15731,
-          "sha256": "1ee5621a825219c1125a9c3f3ac779ac8bfa2fc45668531dbee3a728be13bfb5"
+          "bytes": 15999,
+          "sha256": "d5a7118a878b202adbc50e3436bbe134e5de139f2a9e97176efe9ecc0f446088"
         },
         "hf_model": {
           "path": "hf_model:results/omni_finetune/OMNI_MODEL_COMPARISON.md",
           "exists": true,
-          "bytes": 15731,
-          "sha256": "1ee5621a825219c1125a9c3f3ac779ac8bfa2fc45668531dbee3a728be13bfb5"
+          "bytes": 15999,
+          "sha256": "d5a7118a878b202adbc50e3436bbe134e5de139f2a9e97176efe9ecc0f446088"
         }
       },
       "failures": []
@@ -3763,26 +3812,57 @@
         "path": "repo:results/omni_finetune/QWEN3_FULL_PARAMETER_GATES_20260609.md",
         "exists": true,
         "bytes": 3253,
-        "sha256": "5c0e49adad861e00bede7f9245808e6e68346e7bc51c0b0142d2b99f944f2408"
+        "sha256": "b25f1d8cde814207b4c3234bf07140cf99a0ede29af3f53dbc146aab464e8a9b"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:results/omni_finetune/QWEN3_FULL_PARAMETER_GATES_20260609.md",
           "exists": true,
           "bytes": 3253,
-          "sha256": "5c0e49adad861e00bede7f9245808e6e68346e7bc51c0b0142d2b99f944f2408"
+          "sha256": "b25f1d8cde814207b4c3234bf07140cf99a0ede29af3f53dbc146aab464e8a9b"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:results/omni_finetune/QWEN3_FULL_PARAMETER_GATES_20260609.md",
           "exists": true,
           "bytes": 3253,
-          "sha256": "5c0e49adad861e00bede7f9245808e6e68346e7bc51c0b0142d2b99f944f2408"
+          "sha256": "b25f1d8cde814207b4c3234bf07140cf99a0ede29af3f53dbc146aab464e8a9b"
         },
         "hf_model": {
           "path": "hf_model:results/omni_finetune/QWEN3_FULL_PARAMETER_GATES_20260609.md",
           "exists": true,
           "bytes": 3253,
-          "sha256": "5c0e49adad861e00bede7f9245808e6e68346e7bc51c0b0142d2b99f944f2408"
+          "sha256": "b25f1d8cde814207b4c3234bf07140cf99a0ede29af3f53dbc146aab464e8a9b"
+        }
+      },
+      "failures": []
+    },
+    {
+      "name": "results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md",
+        "exists": true,
+        "bytes": 1793,
+        "sha256": "890430b05ace20375fc9534f923d170c0509037272ba4ef523e3ca2f3c9ac746"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md",
+          "exists": true,
+          "bytes": 1793,
+          "sha256": "890430b05ace20375fc9534f923d170c0509037272ba4ef523e3ca2f3c9ac746"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md",
+          "exists": true,
+          "bytes": 1793,
+          "sha256": "890430b05ace20375fc9534f923d170c0509037272ba4ef523e3ca2f3c9ac746"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md",
+          "exists": true,
+          "bytes": 1793,
+          "sha256": "890430b05ace20375fc9534f923d170c0509037272ba4ef523e3ca2f3c9ac746"
         }
       },
       "failures": []
@@ -7972,6 +8052,37 @@
       },
       "failures": []
     },
+    {
+      "name": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/package_audit.json",
+      "status": "pass",
+      "local": {
+        "path": "repo:results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/package_audit.json",
+        "exists": true,
+        "bytes": 631,
+        "sha256": "7cf478ae33c52bae0ba742e81da8e482e06d0853eecd85f895f447a708f81718"
+      },
+      "mirrors": {
+        "hf_space": {
+          "path": "hf_space:results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/package_audit.json",
+          "exists": true,
+          "bytes": 631,
+          "sha256": "7cf478ae33c52bae0ba742e81da8e482e06d0853eecd85f895f447a708f81718"
+        },
+        "hf_artifacts": {
+          "path": "hf_artifacts:results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/package_audit.json",
+          "exists": true,
+          "bytes": 631,
+          "sha256": "7cf478ae33c52bae0ba742e81da8e482e06d0853eecd85f895f447a708f81718"
+        },
+        "hf_model": {
+          "path": "hf_model:results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/package_audit.json",
+          "exists": true,
+          "bytes": 631,
+          "sha256": "7cf478ae33c52bae0ba742e81da8e482e06d0853eecd85f895f447a708f81718"
+        }
+      },
+      "failures": []
+    },
     {
       "name": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/training/progress.jsonl",
       "status": "pass",
@@ -11574,27 +11685,27 @@
       "local": {
         "path": "repo:RESEARCH_ROADMAP.md",
         "exists": true,
-        "bytes": 14354,
-        "sha256": "7d385916e6d07cfa5f95e80b501fe58237f671711691cc8c792479d233991ef5"
+        "bytes": 14503,
+        "sha256": "bb06fb0ccf336cafb0305883b7f93c2e1af547c9ff04b1fa6fc87481d54bcf61"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:RESEARCH_ROADMAP.md",
           "exists": true,
-          "bytes": 14354,
-          "sha256": "7d385916e6d07cfa5f95e80b501fe58237f671711691cc8c792479d233991ef5"
+          "bytes": 14503,
+          "sha256": "bb06fb0ccf336cafb0305883b7f93c2e1af547c9ff04b1fa6fc87481d54bcf61"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:RESEARCH_ROADMAP.md",
           "exists": true,
-          "bytes": 14354,
-          "sha256": "7d385916e6d07cfa5f95e80b501fe58237f671711691cc8c792479d233991ef5"
+          "bytes": 14503,
+          "sha256": "bb06fb0ccf336cafb0305883b7f93c2e1af547c9ff04b1fa6fc87481d54bcf61"
         },
         "hf_model": {
           "path": "hf_model:RESEARCH_ROADMAP.md",
           "exists": true,
-          "bytes": 14354,
-          "sha256": "7d385916e6d07cfa5f95e80b501fe58237f671711691cc8c792479d233991ef5"
+          "bytes": 14503,
+          "sha256": "bb06fb0ccf336cafb0305883b7f93c2e1af547c9ff04b1fa6fc87481d54bcf61"
         }
       },
       "failures": []
@@ -11605,27 +11716,27 @@
       "local": {
         "path": "repo:PROJECT_STATUS.md",
         "exists": true,
-        "bytes": 13535,
-        "sha256": "595f90e26d75baba46a0827eb2ec38d0c6badb137437f642dff4e88e22b7ca80"
+        "bytes": 13755,
+        "sha256": "342897ae05ceab83d626765c0052c140e414ba25ebda4fce9fb07bb37a2decef"
       },
       "mirrors": {
         "hf_space": {
           "path": "hf_space:PROJECT_STATUS.md",
           "exists": true,
-          "bytes": 13535,
-          "sha256": "595f90e26d75baba46a0827eb2ec38d0c6badb137437f642dff4e88e22b7ca80"
+          "bytes": 13755,
+          "sha256": "342897ae05ceab83d626765c0052c140e414ba25ebda4fce9fb07bb37a2decef"
         },
         "hf_artifacts": {
           "path": "hf_artifacts:PROJECT_STATUS.md",
           "exists": true,
-          "bytes": 13535,
-          "sha256": "595f90e26d75baba46a0827eb2ec38d0c6badb137437f642dff4e88e22b7ca80"
+          "bytes": 13755,
+          "sha256": "342897ae05ceab83d626765c0052c140e414ba25ebda4fce9fb07bb37a2decef"
         },
         "hf_model": {
           "path": "hf_model:PROJECT_STATUS.md",
           "exists": true,
-          "bytes": 13535,
-          "sha256": "595f90e26d75baba46a0827eb2ec38d0c6badb137437f642dff4e88e22b7ca80"
+          "bytes": 13755,
+          "sha256": "342897ae05ceab83d626765c0052c140e414ba25ebda4fce9fb07bb37a2decef"
         }
       },
       "failures": []

metrics/omni_finetune_verified_result.json

@@ -1,98 +1,96 @@
 {
-    "title": "Verified Qwen3-Omni LoRA 128-Episode Held-Out Result",
-    "status": "verified_full_128_episode_diagnostic_result",
-    "status_date": "2026-06-08",
-    "backbone": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
-    "adapter": "Qwen3-Omni LoRA",
-    "dataset": "Ropedia Xperience-10M selected 128-episode pilot",
-    "split_policy": {
-        "unit": "episode",
-        "selected_episode_counts": {
-            "test": 16,
-            "train": 96,
-            "val": 16
-        },
-        "exported_window_counts": {
-            "train": 2848,
-            "val": 512,
-            "test": 448
-        },
-        "exported_episode_counts": {
-            "train": 89,
-            "val": 16,
-            "test": 14
-        },
-        "skipped_selected_episodes": 9,
-        "leakage_policy": "Train, validation, and test are separated by episode/session; test windows are used only for held-out evaluation."
+  "title": "Verified Qwen3-Omni LoRA 128-Episode Held-Out Result",
+  "status": "verified_latest_qwen3_v6_diagnostic_result",
+  "status_date": "2026-06-14",
+  "backbone": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+  "adapter": "Qwen3-Omni LoRA",
+  "dataset": "Ropedia Xperience-10M selected 128-episode pilot",
+  "split_policy": {
+    "unit": "episode",
+    "selected_episode_counts": {
+      "train": 96,
+      "val": 16,
+      "test": 16
     },
-    "training": {
-        "num_processes": 8,
-        "epochs": 4,
-        "lora_rank": 16,
-        "lora_alpha": 32,
-        "lora_dropout": 0.05,
-        "num_train_samples": 2848,
-        "num_val_samples": 512,
-        "history": [
-            {
-                "epoch": 1,
-                "train_loss": 0.40796751019628613,
-                "val_loss": 0.03258896619081497,
-                "global_step": 356
-            },
-            {
-                "epoch": 2,
-                "train_loss": 0.027628723937453012,
-                "val_loss": 0.027754632756114006,
-                "global_step": 712
-            },
-            {
-                "epoch": 3,
-                "train_loss": 0.02446955946807781,
-                "val_loss": 0.026343274861574173,
-                "global_step": 1068
-            },
-            {
-                "epoch": 4,
-                "train_loss": 0.022728607045444712,
-                "val_loss": 0.025629229843616486,
-                "global_step": 1424
-            }
-        ],
-        "loss": "answer-token cross entropy over supervised JSON tokens",
-        "note": "This current Qwen3-Omni LoRA result is the v4 four-epoch full held-out evaluation on the selected 96/16/16 episode setup."
+    "exported_window_counts": {
+      "train": 25629,
+      "val": 4608,
+      "test": 4032
     },
-    "evaluation": {
-        "split": "test",
-        "num_samples": 448,
-        "held_out_episode_count": 14,
-        "json_validity_rate": 1.0,
-        "action_macro_f1": 0.0018678269676001454,
-        "subtask_accuracy": 0.0,
-        "transition_accuracy": 0.9732142857142857,
-        "next_action_accuracy": 0.033482142857142856,
-        "contact_accuracy": 0.7299107142857143,
-        "object_micro_f1": 0.31099781500364165,
-        "quality_target": {
-            "json_validity_rate": 0.98,
-            "status": "met"
-        },
-        "previous_strict_label_v3_action_macro_f1": 0.0021983997167007384,
-        "previous_structured_json_v2_json_validity_rate": 0.9977678571428571
+    "exported_episode_counts": {
+      "train": 89,
+      "val": 16,
+      "test": 14
     },
-    "interpretation": "This is the current verified Qwen3-Omni LoRA diagnostic result for the selected 128-episode setup. The v4 four-epoch package reaches 100% JSON validity and slightly improves next-action, contact, and object metrics versus the prior strict-label v3 package, while action and subtask classification remain weak on held-out episodes. Treat it as a diagnostic baseline and error-analysis source, not as a strong Xperience-10M action recognizer.",
-    "public_package": {
-        "path": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_structured_json_v4_4epoch_full8gpu_lora_eval_test_full",
-        "audit_status": "pass",
-        "contains_raw_xperience10m_data": false,
-        "contains_qwen_base_weights": false,
-        "contains_lora_weights": false,
-        "adapter_weights_repo": "cy0307/ropedia-qwen3-omni-lora-128ep"
+    "skipped_selected_episodes": 9,
+    "leakage_policy": "Train, validation, and test are separated by episode/session; test windows are used only for held-out evaluation."
+  },
+  "training": {
+    "num_processes": 8,
+    "epochs": 2,
+    "lora_rank": 64,
+    "lora_alpha": 128,
+    "lora_dropout": 0.05,
+    "learning_rate": 0.00005,
+    "num_train_samples": 25629,
+    "num_val_samples": 2048,
+    "history": [
+      {
+        "epoch": 1,
+        "train_loss": 0.05208605339353295,
+        "val_loss": 0.026512427255511284,
+        "global_step": 3204
+      },
+      {
+        "epoch": 2,
+        "train_loss": 0.013760763933660042,
+        "val_loss": 0.032345958054065704,
+        "global_step": 6408
+      }
+    ],
+    "loss": "answer-token cross entropy over supervised JSON tokens",
+    "note": "This current Qwen3-Omni LoRA result is the v6 rank64/lr5e-5 dense multiscale held-out evaluation on the selected 96/16/16 episode setup."
+  },
+  "evaluation": {
+    "split": "test",
+    "num_samples": 4032,
+    "held_out_episode_count": 14,
+    "json_validity_rate": 0.9990079365079365,
+    "action_macro_f1": 0.0028830723979596335,
+    "subtask_accuracy": 0.0037313432835820895,
+    "transition_accuracy": 0.9898313492063492,
+    "next_action_accuracy": 0.04305335446381405,
+    "contact_accuracy": 0.8177083333333334,
+    "object_micro_f1": 0.3064982378331287,
+    "quality_target": {
+      "json_validity_rate": 0.98,
+      "status": "met"
     },
-    "required_next_steps": [
-        "Use the v4 predictions for action/subtask error analysis, unseen-label debugging, and hierarchical action-family scoring.",
-        "Use TASK_SUITE_ENHANCEMENT_128.md and docs/data/task_suite_enhancement_128.json for the no-new-episode suite push before requesting more storage.",
-        "Keep the existing Qwen LoRA adapter repository as the weight-bearing artifact and publish future Qwen v5 runs as separate verified packages.",
-        "Use the verified Cosmos3-Super Forward-Dynamics LoRA package as a separate world-model branch: it updates adapter weights over camera-pose proxy future-vision-velocity targets, not Qwen-style JSON action labels."
-    ]
+    "previous_v5_json_validity_rate": 1.0,
+    "previous_v5_action_macro_f1": 0.002289711036077459,
+    "previous_v5_subtask_accuracy": 0.011194029850746268,
+    "previous_v5_next_action_accuracy": 0.053618594823032224,
+    "previous_v5_contact_accuracy": 0.7864583333333334,
+    "previous_v5_object_micro_f1": 0.31614599936244814
+  },
+  "interpretation": "This is the latest verified Qwen3-Omni LoRA diagnostic result for the selected 128-episode setup. The v6 rank64/lr5e-5 package keeps JSON validity above the 98% target and improves action macro-F1 and contact accuracy versus the pinned v5 release row, but slightly regresses JSON validity, subtask accuracy, next-action accuracy, transition accuracy, and object micro-F1. Treat it as the latest diagnostic branch, not as a globally stronger replacement for v5.",
+  "public_package": {
+    "path": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full",
+    "audit_status": "pass",
+    "contains_raw_xperience10m_data": false,
+    "contains_qwen_base_weights": false,
+    "contains_lora_weights": false,
+    "adapter_weights_repo": "cy0307/ropedia-qwen3-omni-lora-128ep"
+  },
+  "release_policy": {
+    "latest_verified_qwen_row": "xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full",
+    "pinned_release_tag": "ropedia-xperience-10m-v5",
+    "pinned_release_reason": "v5 remains the prior stable release tag; v6 is published on main/HF as the latest verified branch and can receive a separate v6 release tag."
+  },
+  "required_next_steps": [
+    "Use results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md before deciding whether v6 should become a formal release tag.",
+    "Use the v6 predictions for action/contact error analysis, and compare v5 for subtask, next-action, and object regressions.",
+    "Keep full-parameter Qwen runs as feasibility gates until there is a storage plan for checkpoints or mergeable full-weight deltas.",
+    "Use the verified Cosmos3-Super Forward-Dynamics LoRA package as a separate world-model branch: it updates adapter weights over camera-pose proxy future-vision-velocity targets, not Qwen-style JSON action labels."
+  ]
 }

metrics/omni_model_comparison.json

@@ -1,6 +1,6 @@
 {
   "title": "Ropedia Xperience-10M Current Result Versions and Model Groups",
-  "generated_at_utc": "2026-06-12T18:14:48+00:00",
+  "generated_at_utc": "2026-06-13T17:41:35+00:00",
   "status": "pass",
   "version_count": 3,
   "model_group_count": 5,
@@ -588,8 +588,8 @@
               "global_step": 3204
             }
           ],
-          "is_current": true,
-          "weights_repository": "https://huggingface.co/cy0307/ropedia-qwen3-omni-lora-128ep"
+          "is_current": false,
+          "weights_repository": "historical diagnostic package; keep separate from the final 128-episode adapter repo"
         },
         {
           "id": "xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full",
@@ -640,8 +640,8 @@
               "global_step": 6408
             }
           ],
-          "is_current": false,
-          "weights_repository": "historical diagnostic package; keep separate from the final 128-episode adapter repo"
+          "is_current": true,
+          "weights_repository": "https://huggingface.co/cy0307/ropedia-qwen3-omni-lora-128ep"
         },
         {
           "id": "xperience10m_qwen3_omni_128ep_structured_json_v2_reuse_full8gpu_lora_eval_test_full",
@@ -1202,8 +1202,8 @@
               "global_step": 3204
             }
           ],
-          "is_current": true,
-          "weights_repository": "https://huggingface.co/cy0307/ropedia-qwen3-omni-lora-128ep"
+          "is_current": false,
+          "weights_repository": "historical diagnostic package; keep separate from the final 128-episode adapter repo"
         },
         {
           "id": "xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full",
@@ -1254,8 +1254,8 @@
               "global_step": 6408
             }
           ],
-          "is_current": false,
-          "weights_repository": "historical diagnostic package; keep separate from the final 128-episode adapter repo"
+          "is_current": true,
+          "weights_repository": "https://huggingface.co/cy0307/ropedia-qwen3-omni-lora-128ep"
         },
         {
           "id": "xperience10m_qwen3_omni_128ep_structured_json_v2_reuse_full8gpu_lora_eval_test_full",
@@ -1753,6 +1753,7 @@
     "Cosmos3-Super now has both a 128-episode base-weight Reasoner evaluation on the JSON task and a fine-tuned forward-dynamics LoRA branch over camera-pose proxy targets."
   ],
   "pending": [
-    "Use the verified Qwen3 v5 dense multiscale full-eval package as the current Qwen row; older Qwen package rows remain historical diagnostics for comparison."
+    "Use the verified Qwen3 v6 rank64/lr5e-5 dense multiscale full-eval package as the latest current Qwen row; the v5 release tag remains pinned as the previous verified release.",
+    "Read results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md before claiming v6 is globally better than v5, because v6 improves action macro-F1 and contact accuracy but regresses subtask, next-action, object micro-F1, and JSON validity slightly."
   ]
 }

metrics/project_packet.json

@@ -1,6 +1,6 @@
 {
     "title": "Ropedia Xperience-10M Task Suite Project Packet",
-    "version": "2026-06-08",
+    "version": "2026-06-14",
     "scope_status": {
         "validated_data": "one public Xperience-10M sample episode",
         "aligned_frames": 5821,
@@ -12,7 +12,7 @@
         "raw_xperience10m_data_in_repo": false,
         "audio_feature_status": "Audio is one of the synchronized source modalities in the current task representation.",
         "qwen3_omni_32_episode_claim": false,
-        "qwen3_omni_status": "The selected 96/16/16 Qwen3-Omni v4 final diagnostic result is verified, meets the strict-JSON target, and still has weak action/subtask metrics that guide the next error-analysis pass.",
+        "qwen3_omni_status": "The selected 96/16/16 Qwen3-Omni v6 diagnostic branch is verified, meets the strict-JSON target, improves action macro-F1/contact accuracy versus v5, and still has weak action/subtask metrics that guide the next error-analysis pass.",
         "cosmos3_super_forward_dynamics_lora_status": "The first Cosmos3-Super fine-tuned adapter branch is verified as a forward-dynamics LoRA over camera-pose proxy targets; it reports loss metrics, not JSON action-label accuracy.",
         "task_suite_enhancement_128_status": "Current no-new-episode enhancement pack recommends multiscale_20s10_40s20_80s40, hierarchical action/subtask targets, label-normalized scoring, and raw-feature shards before adding more episodes."
     },
@@ -118,7 +118,7 @@
                 "scripts/omni/discover_xperience10m_sources.py",
                 "docs/data/omni_finetune_verified_result.json"
             ],
-            "readout": "The selected-episode held-out Qwen3-Omni final diagnostic result is verified and JSON-format reliability meets the 98% target. The same public comparison also includes the verified 128-episode baselines, Cosmos3-Nano compatibility result, Cosmos3-Super Reasoner evaluation, and Cosmos3-Super Forward-Dynamics LoRA package. The next milestone is action/subtask error analysis and stronger model-quality runs on the same split."
+            "readout": "The selected-episode held-out Qwen3-Omni v6 diagnostic branch is verified and JSON-format reliability meets the 98% target. The same public comparison also includes the verified 128-episode baselines, Cosmos3-Nano compatibility result, Cosmos3-Super Reasoner evaluation, and Cosmos3-Super Forward-Dynamics LoRA package. The next milestone is action/subtask error analysis and stronger model-quality runs on the same split."
         },
         {
             "step": 9,
@@ -155,7 +155,7 @@
         "hf_model_baselines": "https://huggingface.co/cy0307/ropedia-xperience-10m-task-baselines"
     },
     "current_reading_notes": [
-        "The first cross-episode Qwen3-Omni v4 diagnostic pilot is verified, but strong model quality is not yet shown; action/subtask metrics remain weak.",
+        "The latest cross-episode Qwen3-Omni v6 diagnostic branch is verified, but strong model quality is not yet shown; action/subtask metrics remain weak and v5 remains stronger on several non-contact metrics.",
         "The current 128-episode suite has a no-new-episode enhancement plan: multiscale_20s10_40s20_80s40 windows, hierarchical labels, label-normalized scoring, and raw-feature shard export.",
         "Cosmos3-Super Forward-Dynamics LoRA is verified as a loss-based world-model adapter branch, not as JSON action-token prediction.",
         "Older Qwen3-Omni setup artifacts are separate from the verified selected-episode diagnostic package.",

metrics/public_surface_qa.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Public Project Surface",
   "status": "pass",
-  "generated_at_utc": "2026-06-12T18:14:49+00:00",
+  "generated_at_utc": "2026-06-13T17:46:37+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": "2026-06-12T17:58:57+00:00"
+          "generated_at_utc": "2026-06-13T17:46:31+00:00"
         },
         "rendered_site_check": {
           "exists": true,
@@ -28,27 +28,27 @@
         "task_surface_integrity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-12T17:58:56+00:00"
+          "generated_at_utc": "2026-06-13T17:42:17+00:00"
         },
         "source_alignment": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-12T17:58:56+00:00"
+          "generated_at_utc": "2026-06-13T17:42:17+00:00"
         },
         "scale_up_status": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-12T17:58:56+00:00"
+          "generated_at_utc": "2026-06-13T17:46:07+00:00"
         },
         "publication_package": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-12T17:59:02+00:00"
+          "generated_at_utc": "2026-06-13T17:44:16+00:00"
         },
         "mirror_parity": {
           "exists": true,
           "status": "pass",
-          "generated_at_utc": "2026-06-12T17:59:14+00:00"
+          "generated_at_utc": "2026-06-12T18:14:59+00:00"
         },
         "live_publication": {
           "exists": true,

metrics/quality_gates.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Release Checks",
   "status": "pass",
-  "generated_at_utc": "2026-06-12T18:14:49+00:00",
+  "generated_at_utc": "2026-06-13T17:46:37+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/qwen3_full_parameter_gates.json

@@ -1,6 +1,6 @@
 {
   "title": "Qwen3-Omni Full-Parameter Feasibility Gates",
-  "generated_at_utc": "2026-06-12T18:14:48+00:00",
+  "generated_at_utc": "2026-06-13T17:41:13+00:00",
   "status": "pass",
   "decision": "full_parameter_feasible_for_guarded_short_runs_not_promoted",
   "interpretation": "The 2026-06-09 gates prove that Qwen3-Omni full-parameter FSDP can load, prepare, run backward/optimizer steps, and complete guarded pilots up to 128 optimizer steps on an 8-GPU remote worker. They do not prove a production full-parameter fine-tune, and they intentionally save no full checkpoints or public weights.",

metrics/qwen3_v5_v6_comparison.json

@@ -0,0 +1,68 @@
+{
+  "title": "Qwen3-Omni v5 versus v6 verified comparison",
+  "status": "pass",
+  "generated_at_utc": "2026-06-14T00:00:00+00:00",
+  "comparison_scope": "Verified Qwen3-Omni LoRA held-out test packages on the same dense multiscale selected 128-episode dataset.",
+  "release_policy": {
+    "latest_verified_qwen_row": "v6",
+    "pinned_release_tag": "ropedia-xperience-10m-v5",
+    "recommendation": "Publish v6 as the latest verified branch and create a separate v6 tag only if the project wants a formal experimental release; do not move the v5 tag."
+  },
+  "runs": {
+    "v5": {
+      "eval_run_id": "xperience10m_qwen3_omni_128ep_multiscale_cap96_v5_full8gpu_lora_eval_test_full",
+      "train_run_id": "xperience10m_qwen3_omni_128ep_multiscale_cap96_v5_full8gpu_lora",
+      "epochs": 1,
+      "eval_samples": 4032,
+      "held_out_episode_count": 14,
+      "metrics": {
+        "json_validity_rate": 1.0,
+        "action_macro_f1": 0.002289711036077459,
+        "subtask_accuracy": 0.011194029850746268,
+        "transition_accuracy": 0.9908234126984127,
+        "next_action_accuracy": 0.053618594823032224,
+        "contact_accuracy": 0.7864583333333334,
+        "object_micro_f1": 0.31614599936244814
+      }
+    },
+    "v6": {
+      "eval_run_id": "xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full",
+      "train_run_id": "xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora",
+      "epochs": 2,
+      "lora_rank": 64,
+      "learning_rate": 0.00005,
+      "eval_samples": 4032,
+      "held_out_episode_count": 14,
+      "metrics": {
+        "json_validity_rate": 0.9990079365079365,
+        "action_macro_f1": 0.0028830723979596335,
+        "subtask_accuracy": 0.0037313432835820895,
+        "transition_accuracy": 0.9898313492063492,
+        "next_action_accuracy": 0.04305335446381405,
+        "contact_accuracy": 0.8177083333333334,
+        "object_micro_f1": 0.3064982378331287
+      }
+    }
+  },
+  "deltas_v6_minus_v5": {
+    "json_validity_rate": -0.0009920634920634888,
+    "action_macro_f1": 0.0005933613618821745,
+    "subtask_accuracy": -0.007462686567164178,
+    "transition_accuracy": -0.0009920634920634888,
+    "next_action_accuracy": -0.010565240359218173,
+    "contact_accuracy": 0.03125,
+    "object_micro_f1": -0.009647761529319436
+  },
+  "wins_for_v6": [
+    "action_macro_f1",
+    "contact_accuracy"
+  ],
+  "wins_for_v5": [
+    "json_validity_rate",
+    "subtask_accuracy",
+    "transition_accuracy",
+    "next_action_accuracy",
+    "object_micro_f1"
+  ],
+  "interpretation": "v6 is the newest verified Qwen LoRA branch and is better for action macro-F1 and contact accuracy, but v5 remains the safer pinned release row for JSON perfection, subtask/next-action accuracy, transition accuracy, and object micro-F1."
+}

metrics/research_roadmap.json

@@ -1,7 +1,7 @@
 {
     "title": "Ropedia Xperience-10M Research Roadmap",
     "summary": "Staged path from the public-sample task lab to verified Qwen3-Omni, Cosmos3-Nano, and Cosmos3-Super diagnostics, same-split 128-episode baseline alignment, a no-new-episode 128-suite enhancement pack, action/subtask error analysis, world/policy branches, and a future Xperience-native embodied foundation model.",
-    "current_decision_point": "Push the current selected 128 episodes harder before requesting more storage: keep the public-sample task suite as the development harness, use the final verified selected-episode Qwen3-Omni v4 diagnostic result and same-split 128-episode simple/NN metadata baselines as structured-task references, read Cosmos3-Nano and Cosmos3-Super Forward-Dynamics LoRA as separate world-model results, export multiscale_20s10_40s20_80s40 windows plus hierarchical action/subtask targets, and defer policy-model experiments until robot-compatible targets are implemented. The Xperience Embodied Foundation Model is a later full-corpus pretraining goal, not a current result.",
+    "current_decision_point": "Push the current selected 128 episodes harder before requesting more storage: keep the public-sample task suite as the development harness, use the latest verified selected-episode Qwen3-Omni v6 diagnostic branch plus the pinned v5 row as structured-task references, read Cosmos3-Nano and Cosmos3-Super Forward-Dynamics LoRA as separate world-model results, continue with hierarchical action/subtask targets and label-normalized scoring, and defer policy-model experiments until robot-compatible targets are implemented. The Xperience Embodied Foundation Model is a later full-corpus pretraining goal, not a current result.",
     "additional_development_directions": {
         "source_document": "ADDITIONAL_DEVELOPMENT_DIRECTIONS.md",
         "source_json": "docs/data/additional_development_directions.json",
@@ -52,8 +52,8 @@
         },
         {
             "id": "qwen3_omni_lora_diagnostic_pilot",
-            "name": "Qwen3-Omni LoRA Final Diagnostic Result",
-            "status": "verified_baseline",
+            "name": "Qwen3-Omni LoRA Latest Diagnostic Branch",
+            "status": "verified_latest_branch",
             "entry_condition": "Selected episodes are prepared locally with no train/test episode leakage.",
             "deliverables": [
                 "dataset JSONL/media manifests",
@@ -64,10 +64,13 @@
                 "metrics",
                 "confusion matrices",
                 "run report",
+                "v5/v6 comparison",
                 "public LoRA adapter repo"
             ],
             "completion_evidence": [
                 "docs/data/omni_finetune_verified_result.json",
+                "docs/data/qwen3_v5_v6_comparison.json",
+                "results/omni_finetune/QWEN3_V5_V6_COMPARISON_20260614.md",
                 "results/omni_finetune/verified_public/",
                 "dataset_manifest.json",
                 "training_metadata.json",

metrics/source_alignment_audit.json

@@ -1,7 +1,7 @@
 {
   "title": "Ropedia Xperience-10M Source Alignment Note",
   "status": "pass",
-  "generated_at_utc": "2026-06-12T18:14:51+00:00",
+  "generated_at_utc": "2026-06-13T17:46:47+00:00",
   "alignment_json": "docs/data/xperience10m_dataset_card_alignment.json",
   "alignment_summary": {
     "full_dataset_repo": "ropedia-ai/xperience-10m",

metrics/summary_metrics.json

@@ -14,7 +14,7 @@
       "visualization.rrd"
     ],
     "access_status": "The gated Xperience-10M dataset is available for selected multi-episode pilot preparation.",
-    "current_scope": "The selected-episode Qwen3-Omni diagnostic pilot is verified on the 96/16/16 split and meets the 98% target for JSON validity; action/subtask quality remains weak, so it is a structured-task baseline. Cosmos3-Nano future-window compatibility and Cosmos3-Super Forward-Dynamics LoRA are also verified as separate world-model diagnostics with different metrics."
+    "current_scope": "The selected-episode Qwen3-Omni v6 diagnostic branch is verified on the 96/16/16 split and meets the 98% target for JSON validity; action/subtask quality remains weak, so it is a structured-task baseline rather than a strong model-quality claim. v6 improves action macro-F1 and contact accuracy versus v5, while v5 remains stronger on JSON validity, subtask, next-action, transition, and object metrics. Cosmos3-Nano future-window compatibility and Cosmos3-Super Forward-Dynamics LoRA are also verified as separate world-model diagnostics with different metrics."
   },
   "models": {
     "motion_action": {

metrics/task_surface_integrity.json

@@ -1,6 +1,6 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-12T18:14:51+00:00",
+  "generated_at_utc": "2026-06-13T17:46:47+00:00",
   "summary": {
     "task_count": 12,
     "expected_task_count": 12,
@@ -64,45 +64,45 @@
       "observed": "timeline_action"
     },
     {
-      "name": "timeline_action: public_field_output_short_is_human_readable",
+      "name": "timeline_action: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "current action class",
+      "value": "20-frame multimodal window",
       "raw_hits": []
     },
     {
-      "name": "timeline_action: public_field_plain_goal_is_human_readable",
+      "name": "timeline_action: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Look at one short multimodal window and name what action is happening now.",
+      "value": "window features -> action label builder -> classifier",
       "raw_hits": []
     },
     {
-      "name": "timeline_action: public_field_display_name_is_human_readable",
+      "name": "timeline_action: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Action Recognition",
+      "value": "Egocentric Action Recognition",
       "raw_hits": []
     },
     {
-      "name": "timeline_action: public_field_input_short_is_human_readable",
+      "name": "timeline_action: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "20-frame multimodal window",
+      "value": "Recognize the current manipulation action from synchronized visual, motion, inertial, pose, and annotation context.",
       "raw_hits": []
     },
     {
-      "name": "timeline_action: public_field_card_blurb_is_human_readable",
+      "name": "timeline_action: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Recognize the current manipulation action from synchronized visual, motion, inertial, pose, and annotation context.",
+      "value": "current action class",
       "raw_hits": []
     },
     {
-      "name": "timeline_action: public_field_process_short_is_human_readable",
+      "name": "timeline_action: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "window features -> action label builder -> classifier",
+      "value": "Look at one short multimodal window and name what action is happening now.",
       "raw_hits": []
     },
     {
-      "name": "timeline_action: public_field_research_name_is_human_readable",
+      "name": "timeline_action: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Egocentric Action Recognition",
+      "value": "Action Recognition",
       "raw_hits": []
     },
     {
@@ -184,45 +184,45 @@
       "observed": "timeline_subtask"
     },
     {
-      "name": "timeline_subtask: public_field_output_short_is_human_readable",
+      "name": "timeline_subtask: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "current procedure step",
+      "value": "20-frame multimodal window",
       "raw_hits": []
     },
     {
-      "name": "timeline_subtask: public_field_plain_goal_is_human_readable",
+      "name": "timeline_subtask: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Predict the higher-level task stage for the current window.",
+      "value": "window features -> subtask label builder -> classifier",
       "raw_hits": []
     },
     {
-      "name": "timeline_subtask: public_field_display_name_is_human_readable",
+      "name": "timeline_subtask: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Procedure Step Recognition",
+      "value": "Temporal Subtask Recognition",
       "raw_hits": []
     },
     {
-      "name": "timeline_subtask: public_field_input_short_is_human_readable",
+      "name": "timeline_subtask: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "20-frame multimodal window",
+      "value": "Recognize the broader activity stage so fine actions become a readable procedure timeline.",
       "raw_hits": []
     },
     {
-      "name": "timeline_subtask: public_field_card_blurb_is_human_readable",
+      "name": "timeline_subtask: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Recognize the broader activity stage so fine actions become a readable procedure timeline.",
+      "value": "current procedure step",
       "raw_hits": []
     },
     {
-      "name": "timeline_subtask: public_field_process_short_is_human_readable",
+      "name": "timeline_subtask: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "window features -> subtask label builder -> classifier",
+      "value": "Predict the higher-level task stage for the current window.",
       "raw_hits": []
     },
     {
-      "name": "timeline_subtask: public_field_research_name_is_human_readable",
+      "name": "timeline_subtask: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Temporal Subtask Recognition",
+      "value": "Procedure Step Recognition",
       "raw_hits": []
     },
     {
@@ -304,45 +304,45 @@
       "observed": "transition_detection"
     },
     {
-      "name": "transition_detection: public_field_output_short_is_human_readable",
+      "name": "transition_detection: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "boundary or steady",
+      "value": "current window with boundary target",
       "raw_hits": []
     },
     {
-      "name": "transition_detection: public_field_plain_goal_is_human_readable",
+      "name": "transition_detection: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Detect whether the current window is near a boundary between actions.",
+      "value": "action changes -> boundary labels -> binary classifier",
       "raw_hits": []
     },
     {
-      "name": "transition_detection: public_field_display_name_is_human_readable",
+      "name": "transition_detection: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Action Boundary Detection",
+      "value": "Temporal Action Segmentation",
       "raw_hits": []
     },
     {
-      "name": "transition_detection: public_field_input_short_is_human_readable",
+      "name": "transition_detection: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "current window with boundary target",
+      "value": "Detect the local moment where the episode changes from one action segment to the next.",
       "raw_hits": []
     },
     {
-      "name": "transition_detection: public_field_card_blurb_is_human_readable",
+      "name": "transition_detection: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Detect the local moment where the episode changes from one action segment to the next.",
+      "value": "boundary or steady",
       "raw_hits": []
     },
     {
-      "name": "transition_detection: public_field_process_short_is_human_readable",
+      "name": "transition_detection: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "action changes -> boundary labels -> binary classifier",
+      "value": "Detect whether the current window is near a boundary between actions.",
       "raw_hits": []
     },
     {
-      "name": "transition_detection: public_field_research_name_is_human_readable",
+      "name": "transition_detection: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Temporal Action Segmentation",
+      "value": "Action Boundary Detection",
       "raw_hits": []
     },
     {
@@ -422,45 +422,45 @@
       "observed": "next_action"
     },
     {
-      "name": "next_action: public_field_output_short_is_human_readable",
+      "name": "next_action: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "action at t+20 frames",
+      "value": "current window at time t",
       "raw_hits": []
     },
     {
-      "name": "next_action: public_field_plain_goal_is_human_readable",
+      "name": "next_action: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Use the current window to guess the action that will happen shortly after it.",
+      "value": "current features -> future label shift -> classifier",
       "raw_hits": []
     },
     {
-      "name": "next_action: public_field_display_name_is_human_readable",
+      "name": "next_action: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Next-Action Prediction",
+      "value": "Short-Horizon Intention Prediction",
       "raw_hits": []
     },
     {
-      "name": "next_action: public_field_input_short_is_human_readable",
+      "name": "next_action: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "current window at time t",
+      "value": "Forecast the near-future action from the current observations only.",
       "raw_hits": []
     },
     {
-      "name": "next_action: public_field_card_blurb_is_human_readable",
+      "name": "next_action: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Forecast the near-future action from the current observations only.",
+      "value": "action at t+20 frames",
       "raw_hits": []
     },
     {
-      "name": "next_action: public_field_process_short_is_human_readable",
+      "name": "next_action: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "current features -> future label shift -> classifier",
+      "value": "Use the current window to guess the action that will happen shortly after it.",
       "raw_hits": []
     },
     {
-      "name": "next_action: public_field_research_name_is_human_readable",
+      "name": "next_action: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Short-Horizon Intention Prediction",
+      "value": "Next-Action Prediction",
       "raw_hits": []
     },
     {
@@ -540,45 +540,45 @@
       "observed": "hand_trajectory_forecast"
     },
     {
-      "name": "hand_trajectory_forecast: public_field_output_short_is_human_readable",
+      "name": "hand_trajectory_forecast: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "future hand-joint trajectory",
+      "value": "current multimodal window",
       "raw_hits": []
     },
     {
-      "name": "hand_trajectory_forecast: public_field_plain_goal_is_human_readable",
+      "name": "hand_trajectory_forecast: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Predict where the hands will move over the next few frames.",
+      "value": "current features -> future mocap target -> regression head",
       "raw_hits": []
     },
     {
-      "name": "hand_trajectory_forecast: public_field_display_name_is_human_readable",
+      "name": "hand_trajectory_forecast: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Hand Trajectory Forecasting",
+      "value": "3D Hand Motion Forecasting",
       "raw_hits": []
     },
     {
-      "name": "hand_trajectory_forecast: public_field_input_short_is_human_readable",
+      "name": "hand_trajectory_forecast: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "current multimodal window",
+      "value": "Predict the future 3D left/right hand path from the current multimodal state.",
       "raw_hits": []
     },
     {
-      "name": "hand_trajectory_forecast: public_field_card_blurb_is_human_readable",
+      "name": "hand_trajectory_forecast: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Predict the future 3D left/right hand path from the current multimodal state.",
+      "value": "future hand-joint trajectory",
       "raw_hits": []
     },
     {
-      "name": "hand_trajectory_forecast: public_field_process_short_is_human_readable",
+      "name": "hand_trajectory_forecast: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "current features -> future mocap target -> regression head",
+      "value": "Predict where the hands will move over the next few frames.",
       "raw_hits": []
     },
     {
-      "name": "hand_trajectory_forecast: public_field_research_name_is_human_readable",
+      "name": "hand_trajectory_forecast: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "3D Hand Motion Forecasting",
+      "value": "Hand Trajectory Forecasting",
       "raw_hits": []
     },
     {
@@ -658,45 +658,45 @@
       "observed": "contact_prediction"
     },
     {
-      "name": "contact_prediction: public_field_output_short_is_human_readable",
+      "name": "contact_prediction: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "contact or no contact",
+      "value": "non-contact, non-caption features",
       "raw_hits": []
     },
     {
-      "name": "contact_prediction: public_field_plain_goal_is_human_readable",
+      "name": "contact_prediction: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Predict whether the body or hand is in contact with something.",
+      "value": "feature filter -> contact target -> binary classifier",
       "raw_hits": []
     },
     {
-      "name": "contact_prediction: public_field_display_name_is_human_readable",
+      "name": "contact_prediction: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Contact State Prediction",
+      "value": "Human-Object Contact Prediction",
       "raw_hits": []
     },
     {
-      "name": "contact_prediction: public_field_input_short_is_human_readable",
+      "name": "contact_prediction: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "non-contact, non-caption features",
+      "value": "Predict whether body or hand contact with the scene is occurring without leaking contact labels.",
       "raw_hits": []
     },
     {
-      "name": "contact_prediction: public_field_card_blurb_is_human_readable",
+      "name": "contact_prediction: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Predict whether body or hand contact with the scene is occurring without leaking contact labels.",
+      "value": "contact or no contact",
       "raw_hits": []
     },
     {
-      "name": "contact_prediction: public_field_process_short_is_human_readable",
+      "name": "contact_prediction: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "feature filter -> contact target -> binary classifier",
+      "value": "Predict whether the body or hand is in contact with something.",
       "raw_hits": []
     },
     {
-      "name": "contact_prediction: public_field_research_name_is_human_readable",
+      "name": "contact_prediction: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Human-Object Contact Prediction",
+      "value": "Contact State Prediction",
       "raw_hits": []
     },
     {
@@ -774,45 +774,45 @@
       "observed": "object_relevance"
     },
     {
-      "name": "object_relevance: public_field_output_short_is_human_readable",
+      "name": "object_relevance: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "relevant object set",
+      "value": "non-caption multimodal features",
       "raw_hits": []
     },
     {
-      "name": "object_relevance: public_field_plain_goal_is_human_readable",
+      "name": "object_relevance: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Predict which objects matter in the current window.",
+      "value": "object vocabulary -> multi-hot labels -> sigmoid heads",
       "raw_hits": []
     },
     {
-      "name": "object_relevance: public_field_display_name_is_human_readable",
+      "name": "object_relevance: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Object Relevance Prediction",
+      "value": "Object-Centric Interaction Recognition",
       "raw_hits": []
     },
     {
-      "name": "object_relevance: public_field_input_short_is_human_readable",
+      "name": "object_relevance: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "non-caption multimodal features",
+      "value": "Infer which objects are relevant to the current manipulation window from non-caption features.",
       "raw_hits": []
     },
     {
-      "name": "object_relevance: public_field_card_blurb_is_human_readable",
+      "name": "object_relevance: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Infer which objects are relevant to the current manipulation window from non-caption features.",
+      "value": "relevant object set",
       "raw_hits": []
     },
     {
-      "name": "object_relevance: public_field_process_short_is_human_readable",
+      "name": "object_relevance: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "object vocabulary -> multi-hot labels -> sigmoid heads",
+      "value": "Predict which objects matter in the current window.",
       "raw_hits": []
     },
     {
-      "name": "object_relevance: public_field_research_name_is_human_readable",
+      "name": "object_relevance: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Object-Centric Interaction Recognition",
+      "value": "Object Relevance Prediction",
       "raw_hits": []
     },
     {
@@ -892,45 +892,45 @@
       "observed": "caption_grounding"
     },
     {
-      "name": "caption_grounding: public_field_output_short_is_human_readable",
+      "name": "caption_grounding: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "ranked matching moments",
+      "value": "text-like query and candidate windows",
       "raw_hits": []
     },
     {
-      "name": "caption_grounding: public_field_plain_goal_is_human_readable",
+      "name": "caption_grounding: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Given a text-like query from annotation, find the matching time window.",
+      "value": "query features -> candidate index -> cosine ranker",
       "raw_hits": []
     },
     {
-      "name": "caption_grounding: public_field_display_name_is_human_readable",
+      "name": "caption_grounding: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Language Grounding",
+      "value": "Language-to-Moment Grounding",
       "raw_hits": []
     },
     {
-      "name": "caption_grounding: public_field_input_short_is_human_readable",
+      "name": "caption_grounding: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "text-like query and candidate windows",
+      "value": "Retrieve the matching time window for an annotation-derived text query.",
       "raw_hits": []
     },
     {
-      "name": "caption_grounding: public_field_card_blurb_is_human_readable",
+      "name": "caption_grounding: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Retrieve the matching time window for an annotation-derived text query.",
+      "value": "ranked matching moments",
       "raw_hits": []
     },
     {
-      "name": "caption_grounding: public_field_process_short_is_human_readable",
+      "name": "caption_grounding: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "query features -> candidate index -> cosine ranker",
+      "value": "Given a text-like query from annotation, find the matching time window.",
       "raw_hits": []
     },
     {
-      "name": "caption_grounding: public_field_research_name_is_human_readable",
+      "name": "caption_grounding: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Language-to-Moment Grounding",
+      "value": "Language Grounding",
       "raw_hits": []
     },
     {
@@ -1008,45 +1008,45 @@
       "observed": "cross_modal_retrieval"
     },
     {
-      "name": "cross_modal_retrieval: public_field_output_short_is_human_readable",
+      "name": "cross_modal_retrieval: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "ranked visual windows",
+      "value": "motion/IMU/pose query; depth/video candidates",
       "raw_hits": []
     },
     {
-      "name": "cross_modal_retrieval: public_field_plain_goal_is_human_readable",
+      "name": "cross_modal_retrieval: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Use one group of modalities to retrieve the matching window from another group.",
+      "value": "modality split -> projection -> nearest-neighbor ranker",
       "raw_hits": []
     },
     {
-      "name": "cross_modal_retrieval: public_field_display_name_is_human_readable",
+      "name": "cross_modal_retrieval: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Cross-Modal Retrieval",
+      "value": "Multimodal Representation Retrieval",
       "raw_hits": []
     },
     {
-      "name": "cross_modal_retrieval: public_field_input_short_is_human_readable",
+      "name": "cross_modal_retrieval: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "motion/IMU/pose query; depth/video candidates",
+      "value": "Use motion, IMU, and camera-pose signals to retrieve the matching depth/video window.",
       "raw_hits": []
     },
     {
-      "name": "cross_modal_retrieval: public_field_card_blurb_is_human_readable",
+      "name": "cross_modal_retrieval: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Use motion, IMU, and camera-pose signals to retrieve the matching depth/video window.",
+      "value": "ranked visual windows",
       "raw_hits": []
     },
     {
-      "name": "cross_modal_retrieval: public_field_process_short_is_human_readable",
+      "name": "cross_modal_retrieval: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "modality split -> projection -> nearest-neighbor ranker",
+      "value": "Use one group of modalities to retrieve the matching window from another group.",
       "raw_hits": []
     },
     {
-      "name": "cross_modal_retrieval: public_field_research_name_is_human_readable",
+      "name": "cross_modal_retrieval: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Multimodal Representation Retrieval",
+      "value": "Cross-Modal Retrieval",
       "raw_hits": []
     },
     {
@@ -1126,45 +1126,45 @@
       "observed": "modality_reconstruction"
     },
     {
-      "name": "modality_reconstruction: public_field_output_short_is_human_readable",
+      "name": "modality_reconstruction: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "reconstructed depth/video vector",
+      "value": "motion, IMU, and camera/pose features",
       "raw_hits": []
     },
     {
-      "name": "modality_reconstruction: public_field_plain_goal_is_human_readable",
+      "name": "modality_reconstruction: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Predict one modality feature block from other modality blocks.",
+      "value": "source-target split -> scaler -> regression head",
       "raw_hits": []
     },
     {
-      "name": "modality_reconstruction: public_field_display_name_is_human_readable",
+      "name": "modality_reconstruction: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Cross-Modal Reconstruction",
+      "value": "Modality Feature Reconstruction",
       "raw_hits": []
     },
     {
-      "name": "modality_reconstruction: public_field_input_short_is_human_readable",
+      "name": "modality_reconstruction: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "motion, IMU, and camera/pose features",
+      "value": "Predict compressed depth/video feature vectors from motion, IMU, and camera-pose features.",
       "raw_hits": []
     },
     {
-      "name": "modality_reconstruction: public_field_card_blurb_is_human_readable",
+      "name": "modality_reconstruction: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Predict compressed depth/video feature vectors from motion, IMU, and camera-pose features.",
+      "value": "reconstructed depth/video vector",
       "raw_hits": []
     },
     {
-      "name": "modality_reconstruction: public_field_process_short_is_human_readable",
+      "name": "modality_reconstruction: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "source-target split -> scaler -> regression head",
+      "value": "Predict one modality feature block from other modality blocks.",
       "raw_hits": []
     },
     {
-      "name": "modality_reconstruction: public_field_research_name_is_human_readable",
+      "name": "modality_reconstruction: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Modality Feature Reconstruction",
+      "value": "Cross-Modal Reconstruction",
       "raw_hits": []
     },
     {
@@ -1244,43 +1244,43 @@
       "observed": "temporal_order"
     },
     {
-      "name": "temporal_order: public_field_output_short_is_human_readable",
+      "name": "temporal_order: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "correct or reversed",
+      "value": "two adjacent windows plus difference vector",
       "raw_hits": []
     },
     {
-      "name": "temporal_order: public_field_plain_goal_is_human_readable",
+      "name": "temporal_order: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Tell whether two nearby windows are in the correct time order.",
+      "value": "pair builder -> feature combiner -> binary classifier",
       "raw_hits": []
     },
     {
-      "name": "temporal_order: public_field_display_name_is_human_readable",
+      "name": "temporal_order: public_field_research_name_is_human_readable",
       "status": "pass",
       "value": "Temporal Order Verification",
       "raw_hits": []
     },
     {
-      "name": "temporal_order: public_field_input_short_is_human_readable",
+      "name": "temporal_order: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "two adjacent windows plus difference vector",
+      "value": "Tell whether two neighboring windows are in chronological order or reversed.",
       "raw_hits": []
     },
     {
-      "name": "temporal_order: public_field_card_blurb_is_human_readable",
+      "name": "temporal_order: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Tell whether two neighboring windows are in chronological order or reversed.",
+      "value": "correct or reversed",
       "raw_hits": []
     },
     {
-      "name": "temporal_order: public_field_process_short_is_human_readable",
+      "name": "temporal_order: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "pair builder -> feature combiner -> binary classifier",
+      "value": "Tell whether two nearby windows are in the correct time order.",
       "raw_hits": []
     },
     {
-      "name": "temporal_order: public_field_research_name_is_human_readable",
+      "name": "temporal_order: public_field_display_name_is_human_readable",
       "status": "pass",
       "value": "Temporal Order Verification",
       "raw_hits": []
@@ -1360,45 +1360,45 @@
       "observed": "misalignment_detection"
     },
     {
-      "name": "misalignment_detection: public_field_output_short_is_human_readable",
+      "name": "misalignment_detection: public_field_input_short_is_human_readable",
       "status": "pass",
-      "value": "aligned or shifted",
+      "value": "motion-side and visual/depth-side feature groups",
       "raw_hits": []
     },
     {
-      "name": "misalignment_detection: public_field_plain_goal_is_human_readable",
+      "name": "misalignment_detection: public_field_process_short_is_human_readable",
       "status": "pass",
-      "value": "Detect when modalities that should match are shifted out of sync.",
+      "value": "aligned/shifted pairs -> feature combiner -> binary classifier",
       "raw_hits": []
     },
     {
-      "name": "misalignment_detection: public_field_display_name_is_human_readable",
+      "name": "misalignment_detection: public_field_research_name_is_human_readable",
       "status": "pass",
-      "value": "Multimodal Synchronization Detection",
+      "value": "Cross-Modal Misalignment Detection",
       "raw_hits": []
     },
     {
-      "name": "misalignment_detection: public_field_input_short_is_human_readable",
+      "name": "misalignment_detection: public_field_card_blurb_is_human_readable",
       "status": "pass",
-      "value": "motion-side and visual/depth-side feature groups",
+      "value": "Detect whether motion and visual/depth streams have been artificially shifted out of sync.",
       "raw_hits": []
     },
     {
-      "name": "misalignment_detection: public_field_card_blurb_is_human_readable",
+      "name": "misalignment_detection: public_field_output_short_is_human_readable",
       "status": "pass",
-      "value": "Detect whether motion and visual/depth streams have been artificially shifted out of sync.",
+      "value": "aligned or shifted",
       "raw_hits": []
     },
     {
-      "name": "misalignment_detection: public_field_process_short_is_human_readable",
+      "name": "misalignment_detection: public_field_plain_goal_is_human_readable",
       "status": "pass",
-      "value": "aligned/shifted pairs -> feature combiner -> binary classifier",
+      "value": "Detect when modalities that should match are shifted out of sync.",
       "raw_hits": []
     },
     {
-      "name": "misalignment_detection: public_field_research_name_is_human_readable",
+      "name": "misalignment_detection: public_field_display_name_is_human_readable",
       "status": "pass",
-      "value": "Cross-Modal Misalignment Detection",
+      "value": "Multimodal Synchronization Detection",
       "raw_hits": []
     },
     {

metrics/website_integrity.json

@@ -1,13 +1,13 @@
 {
   "status": "pass",
-  "generated_at_utc": "2026-06-12T18:14:52+00:00",
+  "generated_at_utc": "2026-06-13T17:46:49+00:00",
   "docs_root": "docs",
   "site_base": "/ropedia-xperience-10m-task-suite/",
   "summary": {
     "html_pages": 4,
     "local_references": 142,
     "external_reference_count": 111,
-    "json_files": 37,
+    "json_files": 38,
     "image_assets_referenced": 22,
     "failure_count": 0
   },
@@ -75,7 +75,7 @@
       "status": "pass",
       "reason": "The project overview should appear before the deeper progress ledger.",
       "overview_index": 67412,
-      "evidence_index": 93026
+      "evidence_index": 93059
     },
     {
       "name": "project_status_links_json",
@@ -137,7 +137,7 @@
       "statuses": [
         "implemented",
         "implemented_for_first_pilot",
-        "verified_baseline",
+        "verified_latest_branch",
         "verified_companion_result",
         "current",
         "active_next_step",
@@ -154,8 +154,8 @@
       "status": "pass",
       "reason": "The evaluation protocol should appear before the deeper evidence ledger.",
       "overview_index": 67412,
-      "protocol_index": 89208,
-      "evidence_index": 93026
+      "protocol_index": 89241,
+      "evidence_index": 93059
     },
     {
       "name": "evaluation_protocol_links_json",
@@ -253,7 +253,7 @@
     },
     {
       "path": "data/artifact_index.json",
-      "bytes": 87230,
+      "bytes": 88913,
       "top_level_type": "dict"
     },
     {
@@ -303,12 +303,12 @@
     },
     {
       "path": "data/omni_finetune_verified_result.json",
-      "bytes": 4431,
+      "bytes": 4325,
       "top_level_type": "dict"
     },
     {
       "path": "data/omni_model_comparison.json",
-      "bytes": 81593,
+      "bytes": 81866,
       "top_level_type": "dict"
     },
     {
@@ -323,12 +323,12 @@
     },
     {
       "path": "data/project_packet.json",
-      "bytes": 10496,
+      "bytes": 10597,
       "top_level_type": "dict"
     },
     {
       "path": "data/project_status.json",
-      "bytes": 23198,
+      "bytes": 23535,
       "top_level_type": "dict"
     },
     {
@@ -351,6 +351,11 @@
       "bytes": 12183,
       "top_level_type": "dict"
     },
+    {
+      "path": "data/qwen3_v5_v6_comparison.json",
+      "bytes": 2814,
+      "top_level_type": "dict"
+    },
     {
       "path": "data/rendered_site_check.json",
       "bytes": 4032,
@@ -373,12 +378,12 @@
     },
     {
       "path": "data/research_roadmap.json",
-      "bytes": 13313,
+      "bytes": 13450,
       "top_level_type": "dict"
     },
     {
       "path": "data/research_roadmap_interactive.json",
-      "bytes": 145083,
+      "bytes": 145234,
       "top_level_type": "dict"
     },
     {
@@ -388,7 +393,7 @@
     },
     {
       "path": "data/scope_claims_audit.json",
-      "bytes": 21325,
+      "bytes": 21795,
       "top_level_type": "dict"
     },
     {
@@ -403,7 +408,7 @@
     },
     {
       "path": "data/summary_metrics.json",
-      "bytes": 27604,
+      "bytes": 27807,
       "top_level_type": "dict"
     },
     {
@@ -423,7 +428,7 @@
     },
     {
       "path": "data/website_integrity.json",
-      "bytes": 15654,
+      "bytes": 15774,
       "top_level_type": "dict"
     },
     {