{
  "id": "state-sanity-20261029",
  "title": "State-conditioned sanity run",
  "date": "2026-10-29",
  "kind": "training",
  "status": "completed",
  "hypothesis": "Test whether state plus optional short history can support efficient next-move training in a fixed one-hour sanity budget.",
  "baseline": "Warm start from CM-5: unchanged backbone and 128 old embedding rows, 384 new embedding rows; fresh AdamW. Not an optimizer resume.",
  "data": "Sealed 10,000,000-position pool: 5,000,000 main-corpus and 5,000,000 curated-corpus positions. Consumed 3,426,304 distinct positions without replacement, exactly 1,713,152 from each source. This is a 50/50 position mix, not a game mix. Validation: 8,192 positions / 24,576 targets; no test evaluation.",
  "config": {
    "run_id": "5e191684-ff0c-4b16-bf23-a6ab42c2daa7",
    "parameters": 86235648,
    "layers": 12,
    "width": 768,
    "heads": 12,
    "vocabulary": 512,
    "input": "FEN state plus optional 16-ply history",
    "input_slots": 122,
    "retained_position_rows": 1024,
    "microbatch_per_gpu": 64,
    "gpus": 2,
    "accumulation": 4,
    "decisions_per_update": 512,
    "precision": "BF16 autocast; FP32 model/AdamW",
    "optimizer": "fresh fused AdamW",
    "selected_step": 6500
  },
  "compute": "Two RTX 4090 GPUs; 2026-10-29 17:42:39 to 18:40:12 UTC (57m32.830s). 6,692 updates, 10,278,912 prediction targets; 992.32 decisions/s all-in.",
  "results": [
    {
      "label": "Initial state-objective NLL",
      "value": 10.821807
    },
    {
      "label": "Best state-objective NLL",
      "value": 0.6436094719295701
    },
    {
      "label": "Updates completed",
      "value": 6692
    },
    {
      "label": "Distinct positions",
      "value": 3426304
    },
    {
      "label": "Prediction targets",
      "value": 10278912
    },
    {
      "label": "All-in decisions per second",
      "value": 992.32
    }
  ],
  "limitations": [
    "Different objective and validation units: NLL is not numerically comparable with full-history experiment losses.",
    "No playing-strength results and no promotion. A separate system-level evaluation is being prepared as EXP-9.",
    "The shorter input did not improve supervised decisions/s relative to the dense full-game objective. High GPU utilization alone is not useful-throughput improvement.",
    "Warm-start exposure remains a limitation. Last weights were not freshly validated; select the best checkpoint.",
    "Exact state-v2 source and reproduction packages are not yet in the public snapshot archive; shared backbone source is identified as lineage only."
  ],
  "checkpoint": "7b63bab559741893b632f456e5f9a8e48b15e48fc9c47c302734da9d613dfe85",
  "sourceSnapshot": "foundation-20261029",
  "history": [
    {
      "step": 0,
      "nll": 10.821807
    },
    {
      "step": 6500,
      "nll": 0.6436094719295701
    }
  ],
  "evidence": [
    {
      "label": "terminal-audit.json",
      "sha256": "757114e47bb8db1f9896bb8db2b5e6ee9ad3b3c3c68b0af105efdf06cca4b96c",
      "selectedFields": {
        "run_id": "5e191684-ff0c-4b16-bf23-a6ab42c2daa7",
        "no_promotion": true,
        "best_checkpoint_sha256": "7b63bab559741893b632f456e5f9a8e48b15e48fc9c47c302734da9d613dfe85",
        "last_checkpoint_sha256": "d5c9a22b67b809c7cb218637137e8fbce15a73217de75fe649faa835c42fc711",
        "last_weights_freshly_validated": false,
        "updates": 6692,
        "decisions": 3426304,
        "source_decisions_each": 1713152
      }
    }
  ]
}