{
  "generated_at_utc": "2026-06-21T07:36:39+00:00",
  "interpretation_rule": "Use the 1-episode line for task construction and reproducibility claims. Use the 128-episode line for held-out comparison and model-branch claims.",
  "lines": [
    {
      "artifact_entry_points": [
        "docs/data/single_episode_task_model_radar.json",
        "docs/data/two_evidence_line_result_summary.json",
        "results/episode_task_suite/summary_report.json",
        "results/episode_task_suite/feature_manifest.json",
        "docs/single_episode_explorer.html"
      ],
      "data_unit": "One public Xperience-10M sample episode",
      "direct_scored_method_task_count": 40,
      "id": "single_public_sample_episode",
      "label": "1 sample episode",
      "method_count": 2,
      "method_task_record_count": 40,
      "methods": [
        {
          "direct_scored_task_count": 20,
          "id": "minimal",
          "label": "Minimal",
          "method_detail": "Single-episode simple heads over the public sample split.",
          "proxy_scored_task_count": 0,
          "result_record_count": 20,
          "scope": "1 public sample episode",
          "scored_task_count": 20,
          "status_counts": {
            "scored": 20
          }
        },
        {
          "direct_scored_task_count": 20,
          "id": "neural_mlp",
          "label": "Neural MLP",
          "method_detail": "Single-episode compact PyTorch MLP heads on the same 20 task contracts.",
          "proxy_scored_task_count": 0,
          "result_record_count": 20,
          "scope": "1 public sample episode",
          "scored_task_count": 20,
          "status_counts": {
            "scored": 20
          }
        }
      ],
      "primary_use": "Inspect raw files, understand each task, rerun local baselines, and debug task quality.",
      "proxy_scored_method_task_count": 0,
      "scored_method_task_count": 40,
      "task_count": 20
    },
    {
      "artifact_entry_points": [
        "docs/data/episode128_task_model_radar.json",
        "docs/data/two_evidence_line_result_summary.json",
        "docs/data/xperience10m_128_episode_feature_index.json",
        "docs/data/omni_model_comparison.json",
        "docs/data/task_method_20_gap_audit.json"
      ],
      "data_unit": "Selected held-out 96/16/16 split with public-safe processed features linked to official gated episode paths",
      "direct_scored_method_task_count": 134,
      "id": "selected_128_episode_surface",
      "label": "128 selected episodes",
      "method_count": 7,
      "method_task_record_count": 140,
      "methods": [
        {
          "direct_scored_task_count": 19,
          "id": "metadata128_simple",
          "label": "128ep Aligned Simple",
          "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
          "proxy_scored_task_count": 1,
          "result_record_count": 20,
          "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
          "scored_task_count": 20,
          "status_counts": {
            "proxy_scored": 1,
            "scored": 19
          }
        },
        {
          "direct_scored_task_count": 19,
          "id": "metadata128_neural_mlp",
          "label": "128ep Aligned NN",
          "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.",
          "proxy_scored_task_count": 1,
          "result_record_count": 20,
          "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available",
          "scored_task_count": 20,
          "status_counts": {
            "proxy_scored": 1,
            "scored": 19
          }
        },
        {
          "direct_scored_task_count": 18,
          "id": "raw128_simple",
          "label": "128ep Raw Simple",
          "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.",
          "proxy_scored_task_count": 2,
          "result_record_count": 20,
          "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
          "scored_task_count": 20,
          "status_counts": {
            "proxy_scored": 2,
            "scored": 18
          }
        },
        {
          "direct_scored_task_count": 18,
          "id": "raw128_neural_mlp",
          "label": "128ep Raw NN",
          "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.",
          "proxy_scored_task_count": 2,
          "result_record_count": 20,
          "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes",
          "scored_task_count": 20,
          "status_counts": {
            "proxy_scored": 2,
            "scored": 18
          }
        },
        {
          "direct_scored_task_count": 20,
          "id": "qwen3_omni_v6_lora",
          "label": "Qwen3-Omni v6 LoRA",
          "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.",
          "proxy_scored_task_count": 0,
          "result_record_count": 20,
          "scope": "128 selected episodes, held-out test",
          "scored_task_count": 20,
          "status_counts": {
            "scored": 20
          }
        },
        {
          "direct_scored_task_count": 20,
          "id": "cosmos3_super_reasoner",
          "label": "Cosmos3-Super Reasoner",
          "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.",
          "proxy_scored_task_count": 0,
          "result_record_count": 20,
          "scope": "128 selected episodes, held-out test",
          "scored_task_count": 20,
          "status_counts": {
            "scored": 20
          }
        },
        {
          "direct_scored_task_count": 20,
          "id": "cosmos3_nano_future_window",
          "label": "Cosmos3-Nano Future Window",
          "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.",
          "proxy_scored_task_count": 0,
          "result_record_count": 20,
          "scope": "128 selected episodes, held-out test",
          "scored_task_count": 20,
          "status_counts": {
            "scored": 20
          }
        }
      ],
      "primary_use": "Compare same-split baselines and model branches while keeping evidence type explicit.",
      "proxy_scored_method_task_count": 6,
      "scored_method_task_count": 140,
      "task_count": 20
    }
  ],
  "proxy_records": [
    {
      "line_id": "selected_128_episode_surface",
      "method": "128ep Raw Simple",
      "metric_key": "macro_f1",
      "reason": "documented compact proxy completion for this raw128 task axis",
      "series_id": "raw128_simple",
      "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/interaction_text_prediction/metrics.json",
      "task_id": "interaction_text_prediction",
      "task_label": "Interaction Text Prediction",
      "task_number": 15
    },
    {
      "line_id": "selected_128_episode_surface",
      "method": "128ep Raw NN",
      "metric_key": "macro_f1",
      "reason": "documented compact proxy completion for this raw128 task axis",
      "series_id": "raw128_neural_mlp",
      "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/interaction_text_prediction/metrics.json",
      "task_id": "interaction_text_prediction",
      "task_label": "Interaction Text Prediction",
      "task_number": 15
    },
    {
      "line_id": "selected_128_episode_surface",
      "method": "128ep Aligned Simple",
      "metric_key": "mrr",
      "reason": "paired camera-view embeddings are absent from the 128 JSONL/feature export; metadata features retrieve the synchronized same-window depth/audio block as a documented compact synchronization proxy",
      "series_id": "metadata128_simple",
      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json",
      "task_id": "camera_view_sync_retrieval",
      "task_label": "Camera-View Synchronization Retrieval",
      "task_number": 19
    },
    {
      "line_id": "selected_128_episode_surface",
      "method": "128ep Aligned NN",
      "metric_key": "mrr",
      "reason": "paired camera-view embeddings are absent from the 128 JSONL/feature export; metadata features retrieve the synchronized same-window depth/audio block as a documented compact synchronization proxy",
      "series_id": "metadata128_neural_mlp",
      "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/camera_view_sync_retrieval/metrics.json",
      "task_id": "camera_view_sync_retrieval",
      "task_label": "Camera-View Synchronization Retrieval",
      "task_number": 19
    },
    {
      "line_id": "selected_128_episode_surface",
      "method": "128ep Raw Simple",
      "metric_key": "mrr",
      "reason": "documented compact proxy completion for this raw128 task axis",
      "series_id": "raw128_simple",
      "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/camera_view_sync_retrieval/metrics.json",
      "task_id": "camera_view_sync_retrieval",
      "task_label": "Camera-View Synchronization Retrieval",
      "task_number": 19
    },
    {
      "line_id": "selected_128_episode_surface",
      "method": "128ep Raw NN",
      "metric_key": "mrr",
      "reason": "documented compact proxy completion for this raw128 task axis",
      "series_id": "raw128_neural_mlp",
      "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/camera_view_sync_retrieval/metrics.json",
      "task_id": "camera_view_sync_retrieval",
      "task_label": "Camera-View Synchronization Retrieval",
      "task_number": 19
    }
  ],
  "reader_policy": {
    "proxy_policy": "Proxy-scored cells stay numeric only when the source artifact and reason are attached; they should not be read as direct raw-target measurements.",
    "selected_128_episode_surface": "Use for held-out comparison, metadata/raw-feature baselines, Qwen3/Cosmos branches, and scale-up decisions.",
    "single_public_sample_episode": "Use for task construction, raw-file inspection, local reproducibility, and controlled Minimal-vs-Neural baseline behavior."
  },
  "source_lines": "docs/data/two_evidence_lines.json",
  "source_matrix": "docs/data/task_method_20_result_matrix.json",
  "status": "pass",
  "summary": {
    "direct_scored_method_task_count": 174,
    "line_count": 2,
    "method_count": 9,
    "method_task_record_count": 180,
    "proxy_scored_method_task_count": 6,
    "scored_method_task_count": 180,
    "task_count": 20
  },
  "title": "Two Evidence-Line Result Summary"
}