{
  "schema_version": 1,
  "result_revision": "2026-09-14",
  "criterion": "Official",
  "protocol": {
    "name": "corrected_causal_continuation",
    "training_seeds": [0, 42, 3072],
    "evaluation_seeds": [0, 1, 42],
    "episodes_per_evaluation_seed": 100,
    "history_boundary": "strictly pre-start actions only; append each policy-executed action exactly once"
  },
  "statistics": "mean and sample standard deviation across training-seed means",
  "results_percent": [
    {
      "cell": "LeWM",
      "inference": "CEM 300x30",
      "pusht": {"mean": 74.56, "sample_std": 3.67},
      "cube": {"mean": 67.33, "sample_std": 1.86},
      "reacher": {"mean": 83.11, "sample_std": 0.96},
      "tworoom": {"mean": 39.67, "sample_std": 8.39},
      "macro": {"mean": 66.17, "sample_std": 2.67}
    },
    {
      "cell": "Inverse only",
      "inference": "Direct",
      "pusht": {"mean": 36.11, "sample_std": 0.19},
      "cube": {"mean": 67.56, "sample_std": 4.03},
      "reacher": {"mean": 90.56, "sample_std": 1.35},
      "tworoom": {"mean": 78.56, "sample_std": 6.68},
      "macro": {"mean": 68.19, "sample_std": 0.67}
    },
    {
      "cell": "Goal intent only",
      "inference": "Direct",
      "pusht": {"mean": 81.78, "sample_std": 0.96},
      "cube": {"mean": 100.00, "sample_std": 0.00},
      "reacher": {"mean": 88.67, "sample_std": 0.33},
      "tworoom": {"mean": 69.22, "sample_std": 7.04},
      "macro": {"mean": 84.92, "sample_std": 1.86}
    },
    {
      "cell": "Goal-displacement INTACT",
      "inference": "Direct",
      "pusht": {"mean": 86.11, "sample_std": 0.96},
      "cube": {"mean": 100.00, "sample_std": 0.00},
      "reacher": {"mean": 97.22, "sample_std": 0.84},
      "tworoom": {"mean": 81.56, "sample_std": 3.67},
      "macro": {"mean": 91.22, "sample_std": 0.51}
    }
  ],
  "manifest_note": "PAPER_E5_* manifests preserve checkpoint identities and hashes; this file is authoritative for corrected-evaluator success rates."
}