{
  "title": "Ropedia Xperience-10M Project Brief",
  "summary": "A concise first-reader brief for the public-sample embodied-AI task lab, the first Qwen3-Omni diagnostic pilot, and the multi-model scale-up path.",
  "research_intent": "Treat the public Xperience-10M sample as a small but real research system, then connect it to verified multi-episode experiments without presenting weak diagnostic results as final model quality.",
  "capability_map": [
    {
      "capability": "Data understanding",
      "evidence": "feature_manifest.json, available_modalities.json, modality atlas, and the episode-window HF viewer"
    },
    {
      "capability": "Task design",
      "evidence": "12 task contracts, task cards, case-study walkthroughs, and four research-direction extension probes"
    },
    {
      "capability": "Evaluation rigor",
      "evidence": "chronological split, per-task metrics, predictions, confusion matrices, leakage notes, and generated takeaways"
    },
    {
      "capability": "Scale-up planning",
      "evidence": "verified 96/16/16 Qwen3-Omni validation-monitored diagnostic pilot, structured-output improvement path, Cosmos 3 branch, and policy-model candidates after action-space conversion"
    }
  ],
  "current_artifacts": [
    {
      "layer": "Data unit",
      "status": "1 public sample episode, 5,821 frames, 1,161 synchronized 20-frame windows"
    },
    {
      "layer": "Modalities",
      "status": "Video-derived features, audio, depth, pose/SLAM, mocap, IMU, calibration, and language-derived features"
    },
    {
      "layer": "Task suite",
      "status": "12 embodied-AI task contracts with inputs, targets, metrics, predictions, and case-study walkthroughs"
    },
    {
      "layer": "Models",
      "status": "Minimal linear/ridge/logistic baselines plus compact PyTorch MLP heads for the same 12 tasks"
    },
    {
      "layer": "Research map",
      "status": "Four Ropedia research directions with direct, proxy, diagnostic, and extension-task coverage"
    },
    {
      "layer": "Scale-up path",
      "status": "A selected 96/16/16 Qwen3-Omni LoRA validation-monitored diagnostic pilot is verified; current model-quality metrics are weak and guide the next structured-output improvement pass"
    }
  ],
  "reading_order": [
    "Start with the website or PROJECT_BRIEF.md to understand the project shape.",
    "Open RESEARCH_ROADMAP.md to see how the work scales from the public sample to multi-episode modeling.",
    "Open EVALUATION_PROTOCOL.md before comparing task scores.",
    "Use RESEARCH_TAKEAWAYS.md for the current metric interpretation.",
    "Inspect results/episode_task_suite/feature_manifest.json to understand one model input.",
    "Use docs/data/omni_finetune_verified_result.json for the current multi-episode Qwen3-Omni pilot result."
  ],
  "scope_boundary": "The public sample is enough to build and verify task definitions, feature contracts, metrics, visualization, and baseline code. The validation-aware multi-episode Qwen3-Omni pilot verifies the training loop but does not yet show strong model quality.",
  "next_stage": "Improve structured JSON reliability and error analysis before larger robustness or alternative-backbone claims.",
  "entry_points": {
    "visual_dashboard": "https://chaoyue0307.github.io/ropedia-xperience-10m-task-suite/",
    "hf_space": "https://huggingface.co/spaces/cy0307/ropedia-xperience-10m-task-suite",
    "artifact_dataset": "https://huggingface.co/datasets/cy0307/ropedia-xperience-10m-task-suite-artifacts",
    "baseline_model_bundle": "https://huggingface.co/cy0307/ropedia-xperience-10m-task-baselines",
    "official_xperience10m_dataset": "https://huggingface.co/datasets/ropedia-ai/xperience-10m"
  }
}