| { |
| "title": "Ropedia Xperience-10M Release Checks", |
| "status": "pass", |
| "generated_at_utc": "2026-06-23T07:26:14+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": [ |
| { |
| "id": "scale_up_status", |
| "title": "Multi-episode pilot status", |
| "command": "python scripts/validate_scope_claims.py", |
| "report": "docs/data/scope_claims_audit.json", |
| "blocks_if": "Setup identifiers are presented as completed held-out metrics.", |
| "shows": "Qwen3-Omni setup artifacts stay distinct from the planned held-out pilot.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "source_alignment", |
| "title": "Source alignment", |
| "command": "python scripts/validate_source_alignment.py", |
| "report": "docs/data/source_alignment_audit.json", |
| "blocks_if": "Official full-dataset facts, sample-card facts, API-listing notes, or project coverage are missing or inconsistent.", |
| "shows": "The repo, website, and Hugging Face cards preserve the Xperience-10M source facts and current project scope.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "website_integrity", |
| "title": "Website integrity", |
| "command": "python scripts/validate_website_integrity.py", |
| "report": "docs/data/website_integrity.json", |
| "blocks_if": "Local links, anchors, JSON bundles, or referenced image assets are missing or invalid.", |
| "shows": "The GitHub Pages / HF static surface is self-consistent before upload.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "rendered_site_check", |
| "title": "Rendered website check", |
| "command": "python scripts/build_rendered_site_check.py --input /tmp/xperience_rendered_site_observations.json", |
| "report": "docs/data/rendered_site_check.json", |
| "blocks_if": "The local rendered site cannot load, switch tabs, deep-link to the walkthrough, update player controls, or stay console-clean.", |
| "shows": "The published static page has a recent browser-level interaction record in addition to static link checks.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "task_surface_integrity", |
| "title": "Task surface integrity", |
| "command": "python scripts/validate_task_surface.py", |
| "report": "docs/data/task_surface_integrity.json", |
| "blocks_if": "Task cards expose raw artifact ids, human-readable task names drift, modality thumbnails are missing, or the interactive task player is not wired to the generated JSON.", |
| "shows": "The public task cards and walkthrough/player stay aligned with generated task-suite metadata.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "evaluation_protocol", |
| "title": "Evaluation protocol", |
| "command": "python scripts/build_evaluation_protocol.py", |
| "report": "docs/data/evaluation_protocol.json", |
| "blocks_if": "Windowing, split policy, leakage controls, task metrics, or current limitations are not explicit.", |
| "shows": "The task evaluation protocol is generated from committed metric artifacts.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "task_method_source_audit", |
| "title": "Task-method source audit", |
| "command": "python scripts/validate_task_method_matrix_sources.py", |
| "report": "docs/data/task_method_20_source_audit.json", |
| "blocks_if": "A scored 20-task matrix cell points to a JSON metric source that does not contain the same metric value.", |
| "shows": "Public 20-task scores remain traceable to their task-specific metric artifacts.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "figure_index", |
| "title": "Figure index", |
| "command": "python scripts/build_figure_index.py", |
| "report": "docs/data/figure_index.json", |
| "blocks_if": "Public figures, charts, or modality thumbnails are missing, unreadable, or lack source-script provenance.", |
| "shows": "Public visual assets have dimensions, SHA-256 hashes, source scripts, and presentation roles.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "brand_assets", |
| "title": "Brand assets", |
| "command": "python scripts/build_brand_assets.py", |
| "report": "docs/data/brand_assets.json", |
| "blocks_if": "The generated logo system, favicon, social card, or app icons are missing or not reproducibly packaged.", |
| "shows": "The same project logo is available for website header, favicon, README, Hugging Face cards, and social previews.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "quality_gate_manifest", |
| "title": "Release-check manifest", |
| "command": "python scripts/build_quality_gates.py", |
| "report": "docs/data/quality_gates.json", |
| "blocks_if": "A public reader cannot see the current release state in one place.", |
| "shows": "The release checklist is explicit, versioned, and mirrored with the repo.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "artifact_index", |
| "title": "Artifact index", |
| "command": "python scripts/build_artifact_index.py", |
| "report": "docs/data/artifact_index.json", |
| "blocks_if": "Project-critical evidence files are missing from the indexed artifact layer.", |
| "shows": "Core project artifacts exist and stable files have SHA-256 hashes.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "publication_package", |
| "title": "Public bundle contents", |
| "command": "python scripts/validate_publication_package.py", |
| "report": "docs/data/publication_audit.json", |
| "blocks_if": "Raw data, caches, heavy archives, credential text, missing required assets, or outdated public-card assets enter public bundles.", |
| "shows": "The repo and prepared HF bundles contain the intended public files for release.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "public_surface_qa", |
| "title": "Public project surface", |
| "command": "python scripts/build_public_surface_qa.py", |
| "report": "docs/data/public_surface_qa.json", |
| "blocks_if": "Repo, website, or Hugging Face presentation loses SEO/social metadata, accessible tab semantics, source links, project-check links, or clear project language.", |
| "shows": "The public repo, website, and Hugging Face cards read as one cohesive research project surface.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| }, |
| { |
| "id": "mirror_parity", |
| "title": "Prepared mirror parity", |
| "command": "python scripts/validate_mirror_parity.py", |
| "report": "docs/data/mirror_parity.json", |
| "blocks_if": "Prepared HF Space, artifact dataset, or model bundle diverges from the repo for critical files.", |
| "shows": "The files staged for GitHub and Hugging Face are synchronized before upload.", |
| "current_report": { |
| "exists": true, |
| "status": "pass" |
| } |
| } |
| ], |
| "post_publish_checks": [ |
| { |
| "id": "live_publication_verifier", |
| "title": "Live publication verifier", |
| "evidence": "python scripts/verify_live_publication.py", |
| "required_result": "live GitHub Pages, GitHub raw, HF Space, artifact dataset, and model mirrors match the current release assets" |
| }, |
| { |
| "id": "github_pages_deploy", |
| "title": "GitHub Pages deployment", |
| "evidence": "gh run list --repo ChaoYue0307/ropedia-xperience-10m-task-suite --limit 5", |
| "required_result": "latest pages-build-deployment run succeeds" |
| }, |
| { |
| "id": "rendered_browser_check", |
| "title": "Rendered browser check", |
| "evidence": "Browser/Playwright page identity, nonblank render, console health, and one local interaction", |
| "required_result": "no relevant console warnings/errors and target links work" |
| } |
| ], |
| "scope_note": "These checks cover public packaging, project status wording, mirror parity, and website integrity. Cross-episode model quality is measured by later held-out evaluation reports." |
| } |
|
|
