{
  "analysis": {
    "analysis_seed": 100931022626831146778288521785567368280967884067454185406339508381044661579902,
    "bootstrap_method": "percentile",
    "bootstrap_resamples": 10000,
    "conditions": {
      "primary-n10-rho05-a05": {
        "contrasts": {
          "learned_minus_arithmetic_mean": {
            "brier": {
              "bootstrap_interval": [
                -0.011742684594713367,
                -0.010884744531473346
              ],
              "confidence_level": 0.95,
              "mean": -0.011328589338622026,
              "replicates": 30,
              "sample_sd": 0.001222378746797391,
              "standard_error": 0.00022317480447860895
            },
            "log_loss": {
              "bootstrap_interval": [
                -0.03451742884698552,
                -0.03084863618587206
              ],
              "confidence_level": 0.975,
              "mean": -0.032867674759805225,
              "replicates": 30,
              "sample_sd": 0.004587418938609299,
              "standard_error": 0.0008375442778009066
            }
          },
          "learned_minus_independent": {
            "brier": {
              "bootstrap_interval": [
                -0.045589797893877,
                -0.04414277359196793
              ],
              "confidence_level": 0.95,
              "mean": -0.04486527004914517,
              "replicates": 30,
              "sample_sd": 0.002071088289504413,
              "standard_error": 0.00037812725824878566
            },
            "log_loss": {
              "bootstrap_interval": [
                -0.6769442219106362,
                -0.6603093849746896
              ],
              "confidence_level": 0.975,
              "mean": -0.6685956434440967,
              "replicates": 30,
              "sample_sd": 0.021063395984086214,
              "standard_error": 0.0038456323727159153
            }
          }
        },
        "methods": {
          "arithmetic_mean": {
            "brier": {
              "bootstrap_interval": [
                0.180181621656072,
                0.1809622312001349
              ],
              "confidence_level": 0.95,
              "mean": 0.18057094086871348,
              "replicates": 30,
              "sample_sd": 0.0011145349550112163,
              "standard_error": 0.00020348531199588287
            },
            "log_loss": {
              "bootstrap_interval": [
                0.5423124947268536,
                0.543966967568978
              ],
              "confidence_level": 0.95,
              "mean": 0.5431576953340395,
              "replicates": 30,
              "sample_sd": 0.002415264809027244,
              "standard_error": 0.00044096500608420956
            }
          },
          "independent": {
            "brier": {
              "bootstrap_interval": [
                0.21278076541091986,
                0.21541134153917224
              ],
              "confidence_level": 0.95,
              "mean": 0.21410762157923663,
              "replicates": 30,
              "sample_sd": 0.003664722683082085,
              "standard_error": 0.0006690837601749713
            },
            "log_loss": {
              "bootstrap_interval": [
                1.1699778231862563,
                1.188024491772579
              ],
              "confidence_level": 0.95,
              "mean": 1.178885664018331,
              "replicates": 30,
              "sample_sd": 0.0256867896859837,
              "standard_error": 0.004689744713634771
            }
          },
          "individual": {
            "brier": {
              "bootstrap_interval": [
                0.1985710308238056,
                0.19981521047464984
              ],
              "confidence_level": 0.95,
              "mean": 0.1991769980107914,
              "replicates": 30,
              "sample_sd": 0.0017444310782865615,
              "standard_error": 0.0003184880838635367
            },
            "log_loss": {
              "bootstrap_interval": [
                0.5808333150444378,
                0.5836493858546652
              ],
              "confidence_level": 0.95,
              "mean": 0.5822494857648821,
              "replicates": 30,
              "sample_sd": 0.004046176432791924,
              "standard_error": 0.0007387273679619742
            }
          },
          "learned": {
            "brier": {
              "bootstrap_interval": [
                0.16850472981113826,
                0.17000499737635785
              ],
              "confidence_level": 0.95,
              "mean": 0.16924235153009146,
              "replicates": 30,
              "sample_sd": 0.002134429741350364,
              "standard_error": 0.00038969177224917054
            },
            "log_loss": {
              "bootstrap_interval": [
                0.5081472115416239,
                0.5125562734324762
              ],
              "confidence_level": 0.95,
              "mean": 0.5102900205742342,
              "replicates": 30,
              "sample_sd": 0.006271674051657668,
              "standard_error": 0.0011450457838042417
            }
          },
          "oracle": {
            "brier": {
              "bootstrap_interval": [
                0.16791572548132586,
                0.16920592289331227
              ],
              "confidence_level": 0.95,
              "mean": 0.1685677319252792,
              "replicates": 30,
              "sample_sd": 0.001839199546302009,
              "standard_error": 0.0003357903597542925
            },
            "log_loss": {
              "bootstrap_interval": [
                0.5057878589747863,
                0.5090179482683956
              ],
              "confidence_level": 0.95,
              "mean": 0.5073890301642033,
              "replicates": 30,
              "sample_sd": 0.004577201878212537,
              "standard_error": 0.0008356789063173402
            }
          },
          "prior": {
            "brier": {
              "bootstrap_interval": [
                0.25,
                0.25
              ],
              "confidence_level": 0.95,
              "mean": 0.25,
              "replicates": 30,
              "sample_sd": 0.0,
              "standard_error": 0.0
            },
            "log_loss": {
              "bootstrap_interval": [
                0.6931471805599453,
                0.6931471805599453
              ],
              "confidence_level": 0.95,
              "mean": 0.6931471805599453,
              "replicates": 30,
              "sample_sd": 0.0,
              "standard_error": 0.0
            }
          }
        }
      }
    },
    "confidence_level": 0.975,
    "multiplicity_note": "Intervals do not jointly cover all returned conditions and metrics.",
    "resampling_unit": "independent_training_and_test_replicate",
    "schema_version": 1,
    "source_experiment": {
      "phase": "production-primary-v1",
      "replicates": 30,
      "status": "locked_synthetic_evaluation",
      "test_count": 10000,
      "train_count": 200
    }
  },
  "analysis_source_sha256": "a8b78a46ef82c942840116136b56ce5dd7e9ed6368513fa033ff0a44439ae08a",
  "input_sha256": "f2dec062747dce7ff114b1ed103536ec54ef4293c4bb7363e48c3f419345e4a2",
  "manifest_sha256": "afd6f762fd2bcde9798fde9358b56027257e91ce46fabc905661a53523fce552",
  "python_version": "3.14.7",
  "verification": {
    "predictions_checked": 1800000,
    "questions_checked": 306000,
    "runs_verified": 30
  }
}