data/project_status.json

{
  "title": "Ropedia Xperience-10M Task Suite Project Status",
  "version": "2026-06-01",
  "decision": "public_sample_pipeline_verified_multi_episode_omni_data_gated",
  "scope_boundary": {
    "validated_episode_count": 1,
    "aligned_frames": 5821,
    "sliding_windows": 1161,
    "current_feature_dimensions": 8378,
    "core_task_count": 12,
    "neural_head_count": 12,
    "direction_extension_probe_count": 4,
    "audio_featurized": false,
    "raw_xperience10m_data_redistributed": false,
    "qwen3_omni_32_episode_claim": false
  },
  "rows": [
    {
      "area": "Public-sample pipeline",
      "status": "verified",
      "evidence": [
        "results/episode_task_suite/summary_report.json",
        "results/episode_task_suite/windows.csv",
        "results/episode_task_suite/feature_manifest.json"
      ],
      "readout": "One public Xperience-10M sample episode is converted into 5,821 frames, 1,161 aligned 20-frame windows, and an 8,378-dimensional current feature contract."
    },
    {
      "area": "Task suite",
      "status": "verified",
      "evidence": [
        "scripts/episode_task_suite.py",
        "results/episode_task_suite/",
        "docs/data/summary_metrics.json"
      ],
      "readout": "All 12 task contracts have committed metrics, predictions, and minimal baseline outputs."
    },
        {
            "area": "Neural heads",
            "status": "verified",
            "evidence": [
                "scripts/neural_task_models.py",
                "results/episode_task_suite/neural_mlp/"
            ],
            "readout": "Each task also has a compact PyTorch MLP run over the same feature tensor and chronological split."
        },
        {
            "area": "Evaluation protocol",
            "status": "verified",
            "evidence": [
                "EVALUATION_PROTOCOL.md",
                "docs/data/evaluation_protocol.json",
                "scripts/build_evaluation_protocol.py"
            ],
            "readout": "Windowing, chronological split, per-task metrics, leakage controls, and current limitations are generated from committed metric artifacts."
        },
        {
            "area": "Research takeaways",
            "status": "verified",
            "evidence": [
                "RESEARCH_TAKEAWAYS.md",
                "docs/data/research_takeaways.json",
                "scripts/build_research_takeaways.py"
            ],
            "readout": "The main result interpretation is generated from committed metrics: chronological class shift, neural gains on dynamics/order/alignment, open retrieval/reconstruction problems, and the need for held-out episodes."
        },
        {
            "area": "Research roadmap",
            "status": "current",
            "evidence": [
                "RESEARCH_ROADMAP.md",
                "docs/data/research_roadmap.json"
            ],
            "readout": "The staged path connects public-sample task development to multi-episode data staging, the 32-episode Qwen3-Omni LoRA pilot, robustness runs, and larger omni-model extensions."
        },
        {
            "area": "Official dataset wording",
            "status": "verified",
      "evidence": [
        "XPERIENCE10M_DATASET_CARD_ALIGNMENT.md",
        "docs/data/xperience10m_dataset_card_alignment.json"
      ],
            "readout": "Public wording is aligned to the official gated Xperience-10M dataset card, public sample card, and HF API metadata, including modalities, scale, access path, sample license/tooling, and current project coverage."
        },
        {
            "area": "Source alignment",
            "status": "verified",
            "evidence": [
                "SOURCE_ALIGNMENT_AUDIT.md",
                "docs/data/source_alignment_audit.json",
                "scripts/validate_source_alignment.py"
            ],
            "readout": "Source facts, sample details, API-listing notes, and project coverage are checked across repo docs, website, and HF cards."
        },
        {
            "area": "Website and HF mirrors",
      "status": "verified",
      "evidence": [
        "docs/data/website_integrity.json",
        "docs/data/mirror_parity.json",
        "docs/data/live_publication_status.json"
      ],
      "readout": "Local website links/assets pass, prepared mirrors match, and public GitHub/HF URLs have been checked after upload."
    },
    {
      "area": "Publication package",
      "status": "verified",
      "evidence": [
        "docs/data/publication_audit.json",
        "QUALITY_GATES.md",
        "docs/data/quality_gates.json"
      ],
      "readout": "Public bundles are checked for raw-data exclusion, cache exclusion, heavy-archive exclusion, token-string scanning, and stale presentation copy."
    },
    {
      "area": "Reproducibility",
      "status": "verified_for_public_sample",
      "evidence": [
        "REPRODUCIBILITY.md",
        "docs/data/reproducibility_matrix.json",
        "notes/reproducibility_audit.md"
      ],
      "readout": "The public sample workflow has explicit commands, expected outputs, and exact-match reproduction evidence."
    },
    {
      "area": "Qwen3-Omni fine-tuning",
      "status": "data_gated_full_metrics_pending",
      "evidence": [
        "results/omni_finetune/DATA_ACCESS_STATUS.md",
        "results/omni_finetune/MULTI_EPISODE_ACCESS_STATUS.md"
      ],
      "readout": "The 32-episode LoRA pilot is prepared, with final held-out metrics pending gated data access, manifest construction, training, and held-out evaluation."
    },
    {
      "area": "Raw Xperience-10M redistribution",
      "status": "not_included",
      "evidence": [
        "DATA_NOTICE.md",
        "docs/data/publication_audit.json"
      ],
      "readout": "Raw MP4, HDF5, RRD files, private gated data, and full Qwen weights are intentionally excluded."
    }
  ],
  "fast_research_route": [
    "Read PROJECT_STATUS.md and EVIDENCE_CONTRACT.md to establish what is implemented.",
        "Open docs/data/project_packet.json for the machine-readable project path.",
        "Inspect RESEARCH_TAKEAWAYS.md and docs/data/research_takeaways.json before interpreting model scores.",
        "Inspect RESEARCH_ROADMAP.md and docs/data/research_roadmap.json for the staged path from public-sample task work to multi-episode modeling.",
        "Inspect docs/data/summary_metrics.json and results/episode_task_suite/neural_mlp/ to check the 12-task outputs.",
        "Inspect EVALUATION_PROTOCOL.md before judging task metrics or leakage controls.",
        "Inspect SOURCE_ALIGNMENT_AUDIT.md before judging source-card consistency across public surfaces.",
        "Inspect XPERIENCE10M_DATASET_CARD_ALIGNMENT.md before judging dataset wording.",
    "Inspect results/omni_finetune/DATA_ACCESS_STATUS.md before judging Qwen3-Omni scale-up status."
  ],
  "current_reading_notes": [
    "Cross-episode generalization is evaluated in the later multi-episode stage.",
    "Historical 32ep path names refer to setup files, not completed 32-episode training results.",
    "The current reconstruction task reconstructs feature vectors, not pixel-depth, mesh, NeRF, or Gaussian reconstruction.",
    "Audio is documented and visualized, but it is not yet part of the current 8,378-dimensional baseline feature vector."
  ]
}