{
  "accuracy": 0.8831168831168831,
  "brier_mean": 0.17388059732042813,
  "calibration_n": 231,
  "complete": true,
  "cost_basis": [
    "no_billable_account_public_endpoint"
  ],
  "coverage": 1.0,
  "ece": {
    "bins": [
      {
        "accuracy": null,
        "hi": 0.1,
        "lo": 0.0,
        "mean_confidence": null,
        "n": 0
      },
      {
        "accuracy": null,
        "hi": 0.2,
        "lo": 0.1,
        "mean_confidence": null,
        "n": 0
      },
      {
        "accuracy": 0.375,
        "hi": 0.3,
        "lo": 0.2,
        "mean_confidence": 0.25595494387562745,
        "n": 8
      },
      {
        "accuracy": 0.14285714285714285,
        "hi": 0.4,
        "lo": 0.3,
        "mean_confidence": 0.3297851132949228,
        "n": 7
      },
      {
        "accuracy": 0.6,
        "hi": 0.5,
        "lo": 0.4,
        "mean_confidence": 0.43664669932552147,
        "n": 10
      },
      {
        "accuracy": 0.7058823529411765,
        "hi": 0.6,
        "lo": 0.5,
        "mean_confidence": 0.544120172237359,
        "n": 17
      },
      {
        "accuracy": 0.8125,
        "hi": 0.7,
        "lo": 0.6,
        "mean_confidence": 0.6546157628392665,
        "n": 16
      },
      {
        "accuracy": 0.95,
        "hi": 0.8,
        "lo": 0.7,
        "mean_confidence": 0.7476094342235899,
        "n": 20
      },
      {
        "accuracy": 0.9259259259259259,
        "hi": 0.9,
        "lo": 0.8,
        "mean_confidence": 0.8653082190143647,
        "n": 27
      },
      {
        "accuracy": 0.9920634920634921,
        "hi": 1.0,
        "lo": 0.9,
        "mean_confidence": 0.9633948871674165,
        "n": 126
      }
    ],
    "ece": 0.07994470880686899,
    "n": 231
  },
  "latency": {
    "n": 231,
    "p50_s": 0.21858379500008596,
    "p95_s": 1.5345631805002995
  },
  "latency_failures": {
    "n": 0,
    "p50_s": null,
    "p95_s": null
  },
  "ledger_charged_usd": 0.0,
  "macro_accuracy": 0.8852705019629684,
  "model_identities": [
    "decision-medium"
  ],
  "n_attempted": 231,
  "n_correct": 204,
  "n_planned": 231,
  "n_renormalized": 0,
  "n_scorable": 231,
  "n_valid": 231,
  "operational_success": 1.0,
  "ordinal_mae": 0.15935163111560383,
  "paraphrase_consistency": {
    "agree": 35,
    "agreement": 0.9722222222222222,
    "both_correct_rate_all_pairs": 0.9722222222222222,
    "both_valid": 36,
    "pairs": 36
  },
  "per_family": {
    "adequacy": {
      "accuracy": 0.9166666666666666,
      "brier_mean": 0.16264464567147735,
      "calibration_n": 12,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 0.6666666666666666,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.5620667012484599,
            "n": 3
          },
          {
            "accuracy": 1.0,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6926419831347361,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7486761108579822,
            "n": 2
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8933094060543488,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9600966390610968,
            "n": 5
          }
        ],
        "ece": 0.1191677575036739,
        "n": 12
      },
      "latency": {
        "n": 12,
        "p50_s": 0.21708322949962167,
        "p95_s": 0.21958271000085006
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 12,
      "n_correct": 11,
      "n_planned": 12,
      "n_renormalized": 0,
      "n_scorable": 12,
      "n_valid": 12,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "adversarial": {
      "accuracy": 1.0,
      "brier_mean": 0.02147913858770016,
      "calibration_n": 6,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7729575833605401,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8436883703095561,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9397783116556646,
            "n": 4
          }
        ],
        "ece": 0.10404013328454087,
        "n": 6
      },
      "latency": {
        "n": 6,
        "p50_s": 0.687402278999798,
        "p95_s": 1.2077261487502255
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 6,
      "n_correct": 6,
      "n_planned": 6,
      "n_renormalized": 0,
      "n_scorable": 6,
      "n_valid": 6,
      "operational_success": 1.0,
      "ordinal_mae": 0.12498961013257048,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "ambiguous": {
      "accuracy": 0.8571428571428571,
      "brier_mean": 0.21781633320694474,
      "calibration_n": 7,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": 0.46074320252123346,
            "n": 1
          },
          {
            "accuracy": 0.0,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.5964432224654873,
            "n": 1
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.758214144226258,
            "n": 2
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8725905572715923,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9669272131950774,
            "n": 2
          }
        ],
        "ece": 0.2589752496899987,
        "n": 7
      },
      "latency": {
        "n": 7,
        "p50_s": 0.21855992199925822,
        "p95_s": 0.9147610416002856
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 7,
      "n_correct": 6,
      "n_planned": 7,
      "n_renormalized": 0,
      "n_scorable": 7,
      "n_valid": 7,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "extraction": {
      "accuracy": 1.0,
      "brier_mean": 0.0013421247567715038,
      "calibration_n": 24,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9715361228706377,
            "n": 24
          }
        ],
        "ece": 0.02846387712936227,
        "n": 24
      },
      "latency": {
        "n": 24,
        "p50_s": 0.21347228000104224,
        "p95_s": 0.22208953325143738
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 24,
      "n_correct": 24,
      "n_planned": 24,
      "n_renormalized": 0,
      "n_scorable": 24,
      "n_valid": 24,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "fact": {
      "accuracy": 1.0,
      "brier_mean": 0.002724952817468707,
      "calibration_n": 12,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.965341067263609,
            "n": 12
          }
        ],
        "ece": 0.03465893273639098,
        "n": 12
      },
      "latency": {
        "n": 12,
        "p50_s": 0.2177023165004357,
        "p95_s": 0.22845289710048747
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 12,
      "n_correct": 12,
      "n_planned": 12,
      "n_renormalized": 0,
      "n_scorable": 12,
      "n_valid": 12,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "intent": {
      "accuracy": 1.0,
      "brier_mean": 0.009758254186063013,
      "calibration_n": 24,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6993083638267495,
            "n": 1
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8675616866841231,
            "n": 2
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.964999862451638,
            "n": 21
          }
        ],
        "ece": 0.05419046463835855,
        "n": 24
      },
      "latency": {
        "n": 24,
        "p50_s": 0.2140641610003513,
        "p95_s": 0.2231446215008873
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 24,
      "n_correct": 24,
      "n_planned": 24,
      "n_renormalized": 0,
      "n_scorable": 24,
      "n_valid": 24,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "judge_hard": {
      "accuracy": 0.9411764705882353,
      "brier_mean": 0.2330549578604239,
      "calibration_n": 17,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.5360955052256952,
            "n": 3
          },
          {
            "accuracy": 1.0,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6605400174675301,
            "n": 3
          },
          {
            "accuracy": 1.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7310585786300049,
            "n": 2
          },
          {
            "accuracy": 0.8333333333333334,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8502355969264647,
            "n": 6
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9376951392579799,
            "n": 3
          }
        ],
        "ece": 0.1903708493203037,
        "n": 17
      },
      "latency": {
        "n": 17,
        "p50_s": 0.20071710599950165,
        "p95_s": 0.40699049959912303
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 17,
      "n_correct": 16,
      "n_planned": 17,
      "n_renormalized": 0,
      "n_scorable": 17,
      "n_valid": 17,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "long_policy": {
      "accuracy": 0.8421052631578947,
      "brier_mean": 0.37287762317711176,
      "calibration_n": 19,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": 0.22442754228684655,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": 0.31283638571410965,
            "n": 1
          },
          {
            "accuracy": 0.6,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": 0.4193208964205217,
            "n": 5
          },
          {
            "accuracy": 0.8,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.5417293375335148,
            "n": 5
          },
          {
            "accuracy": 1.0,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6090125731919687,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7392890512295184,
            "n": 3
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8626221731586058,
            "n": 3
          },
          {
            "accuracy": null,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": null,
            "n": 0
          }
        ],
        "ece": 0.2759336134669747,
        "n": 19
      },
      "latency": {
        "n": 19,
        "p50_s": 1.3997882029998436,
        "p95_s": 2.098419081499196
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 19,
      "n_correct": 16,
      "n_planned": 19,
      "n_renormalized": 0,
      "n_scorable": 19,
      "n_valid": 19,
      "operational_success": 1.0,
      "ordinal_mae": 0.45926189423191066,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "multi_hop": {
      "accuracy": 0.7777777777777778,
      "brier_mean": 0.3339428580035161,
      "calibration_n": 18,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 0.5,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": 0.2687583256416153,
            "n": 2
          },
          {
            "accuracy": 0.0,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": 0.3200120674268267,
            "n": 2
          },
          {
            "accuracy": 1.0,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": 0.4352711293911737,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.5091602097092707,
            "n": 2
          },
          {
            "accuracy": 0.5,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6464075608078717,
            "n": 2
          },
          {
            "accuracy": 1.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7472210815029732,
            "n": 5
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8793432025803274,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9604376252440875,
            "n": 3
          }
        ],
        "ece": 0.24694275391938864,
        "n": 18
      },
      "latency": {
        "n": 18,
        "p50_s": 0.3213424514997314,
        "p95_s": 1.32010343535012
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 18,
      "n_correct": 14,
      "n_planned": 18,
      "n_renormalized": 0,
      "n_scorable": 18,
      "n_valid": 18,
      "operational_success": 1.0,
      "ordinal_mae": 0.21521003292817387,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "ordinal": {
      "accuracy": 1.0,
      "brier_mean": 0.00520444465125537,
      "calibration_n": 12,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9430657463170716,
            "n": 12
          }
        ],
        "ece": 0.05693425368292837,
        "n": 12
      },
      "latency": {
        "n": 12,
        "p50_s": 0.21340739050083357,
        "p95_s": 0.2468797694506065
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 12,
      "n_correct": 12,
      "n_planned": 12,
      "n_renormalized": 0,
      "n_scorable": 12,
      "n_valid": 12,
      "operational_success": 1.0,
      "ordinal_mae": 0.06209043374233167,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "policy": {
      "accuracy": 1.0,
      "brier_mean": 0.04023651543090801,
      "calibration_n": 12,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6859103411550646,
            "n": 2
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8888360061630532,
            "n": 3
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9719461047045929,
            "n": 7
          }
        ],
        "ece": 0.09650404718904676,
        "n": 12
      },
      "latency": {
        "n": 12,
        "p50_s": 0.21283611899980315,
        "p95_s": 13.76410637669986
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 12,
      "n_correct": 12,
      "n_planned": 12,
      "n_renormalized": 0,
      "n_scorable": 12,
      "n_valid": 12,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "probability": {
      "accuracy": 0.8,
      "brier_mean": 0.4404549320196618,
      "calibration_n": 10,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.5541984537026645,
            "n": 1
          },
          {
            "accuracy": 1.0,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6350351933614518,
            "n": 2
          },
          {
            "accuracy": 1.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7632029218849571,
            "n": 2
          },
          {
            "accuracy": 0.6666666666666666,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8354966434681792,
            "n": 3
          },
          {
            "accuracy": 0.5,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.916099769988311,
            "n": 2
          }
        ],
        "ece": 0.29880147861856776,
        "n": 10
      },
      "latency": {
        "n": 10,
        "p50_s": 1.3118648220006435,
        "p95_s": 1.674036793000232
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 10,
      "n_correct": 8,
      "n_planned": 10,
      "n_renormalized": 0,
      "n_scorable": 10,
      "n_valid": 10,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "routing": {
      "accuracy": 1.0,
      "brier_mean": 0.009240877440215378,
      "calibration_n": 12,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8787478975111437,
            "n": 4
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9502562117534098,
            "n": 8
          }
        ],
        "ece": 0.07357989299401224,
        "n": 12
      },
      "latency": {
        "n": 12,
        "p50_s": 0.23803264799971657,
        "p95_s": 1.4357894898999803
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 12,
      "n_correct": 12,
      "n_planned": 12,
      "n_renormalized": 0,
      "n_scorable": 12,
      "n_valid": 12,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "routing_hard": {
      "accuracy": 1.0,
      "brier_mean": 0.0015139575377800941,
      "calibration_n": 5,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9671320340975906,
            "n": 5
          }
        ],
        "ece": 0.03286796590240937,
        "n": 5
      },
      "latency": {
        "n": 5,
        "p50_s": 0.2117115230012132,
        "p95_s": 0.21383038779931668
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 5,
      "n_correct": 5,
      "n_planned": 5,
      "n_renormalized": 0,
      "n_scorable": 5,
      "n_valid": 5,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "temporal_numeric": {
      "accuracy": 0.13333333333333333,
      "brier_mean": 0.7832557743071475,
      "calibration_n": 15,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 0.2,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": 0.2571390714869885,
            "n": 5
          },
          {
            "accuracy": 0.0,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": 0.33890881812417417,
            "n": 4
          },
          {
            "accuracy": 0.0,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": 0.4471442911532385,
            "n": 2
          },
          {
            "accuracy": 0.0,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.5467381519846138,
            "n": 1
          },
          {
            "accuracy": 0.5,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6441928295732188,
            "n": 2
          },
          {
            "accuracy": 0.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7549149868676283,
            "n": 1
          },
          {
            "accuracy": null,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": null,
            "n": 0
          }
        ],
        "ece": 0.27504386734911973,
        "n": 15
      },
      "latency": {
        "n": 15,
        "p50_s": 0.23321098899941717,
        "p95_s": 2.3723114913995196
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 15,
      "n_correct": 2,
      "n_planned": 15,
      "n_renormalized": 0,
      "n_scorable": 15,
      "n_valid": 15,
      "operational_success": 1.0,
      "ordinal_mae": 0.3727883693553482,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "tool_selection": {
      "accuracy": 1.0,
      "brier_mean": 0.0004656692263069889,
      "calibration_n": 12,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.981743734359022,
            "n": 12
          }
        ],
        "ece": 0.018256265640978042,
        "n": 12
      },
      "latency": {
        "n": 12,
        "p50_s": 0.21899352399941563,
        "p95_s": 0.22537494965008592
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 12,
      "n_correct": 12,
      "n_planned": 12,
      "n_renormalized": 0,
      "n_scorable": 12,
      "n_valid": 12,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "tradeoff": {
      "accuracy": 0.6666666666666666,
      "brier_mean": 0.3610780784089173,
      "calibration_n": 6,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": 0.4795595969337222,
            "n": 1
          },
          {
            "accuracy": 0.0,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.5312093733737562,
            "n": 1
          },
          {
            "accuracy": 0.5,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6340886915385033,
            "n": 2
          },
          {
            "accuracy": null,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8809986819154472,
            "n": 2
          },
          {
            "accuracy": null,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": null,
            "n": 0
          }
        ],
        "ece": 0.2596382992810244,
        "n": 6
      },
      "latency": {
        "n": 6,
        "p50_s": 0.724976662500012,
        "p95_s": 1.3624804334995133
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 6,
      "n_correct": 4,
      "n_planned": 6,
      "n_renormalized": 0,
      "n_scorable": 6,
      "n_valid": 6,
      "operational_success": 1.0,
      "ordinal_mae": null,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    },
    "trap": {
      "accuracy": 1.0,
      "brier_mean": 0.0269012123203273,
      "calibration_n": 8,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7340200209209016,
            "n": 2
          },
          {
            "accuracy": null,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 1.0,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9771173080316468,
            "n": 6
          }
        ],
        "ece": 0.08365701374603954,
        "n": 8
      },
      "latency": {
        "n": 8,
        "p50_s": 0.20171799050058326,
        "p95_s": 0.21115064904943212
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 8,
      "n_correct": 8,
      "n_planned": 8,
      "n_renormalized": 0,
      "n_scorable": 8,
      "n_valid": 8,
      "operational_success": 1.0,
      "ordinal_mae": 0.49173235429297507,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    }
  },
  "price_per_1000_decisions_usd": null,
  "probability_sources": [
    "native"
  ],
  "schema_validity": 1.0,
  "schema_validity_strict": 1.0,
  "splits": {
    "public": {
      "accuracy": 0.8831168831168831,
      "brier_mean": 0.17388059732042813,
      "calibration_n": 231,
      "cost_basis": [
        "no_billable_account_public_endpoint"
      ],
      "coverage": 1.0,
      "ece": {
        "bins": [
          {
            "accuracy": null,
            "hi": 0.1,
            "lo": 0.0,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": null,
            "hi": 0.2,
            "lo": 0.1,
            "mean_confidence": null,
            "n": 0
          },
          {
            "accuracy": 0.375,
            "hi": 0.3,
            "lo": 0.2,
            "mean_confidence": 0.25595494387562745,
            "n": 8
          },
          {
            "accuracy": 0.14285714285714285,
            "hi": 0.4,
            "lo": 0.3,
            "mean_confidence": 0.3297851132949228,
            "n": 7
          },
          {
            "accuracy": 0.6,
            "hi": 0.5,
            "lo": 0.4,
            "mean_confidence": 0.43664669932552147,
            "n": 10
          },
          {
            "accuracy": 0.7058823529411765,
            "hi": 0.6,
            "lo": 0.5,
            "mean_confidence": 0.544120172237359,
            "n": 17
          },
          {
            "accuracy": 0.8125,
            "hi": 0.7,
            "lo": 0.6,
            "mean_confidence": 0.6546157628392665,
            "n": 16
          },
          {
            "accuracy": 0.95,
            "hi": 0.8,
            "lo": 0.7,
            "mean_confidence": 0.7476094342235899,
            "n": 20
          },
          {
            "accuracy": 0.9259259259259259,
            "hi": 0.9,
            "lo": 0.8,
            "mean_confidence": 0.8653082190143647,
            "n": 27
          },
          {
            "accuracy": 0.9920634920634921,
            "hi": 1.0,
            "lo": 0.9,
            "mean_confidence": 0.9633948871674165,
            "n": 126
          }
        ],
        "ece": 0.07994470880686899,
        "n": 231
      },
      "latency": {
        "n": 231,
        "p50_s": 0.21858379500008596,
        "p95_s": 1.5345631805002995
      },
      "latency_failures": {
        "n": 0,
        "p50_s": null,
        "p95_s": null
      },
      "n_attempted": 231,
      "n_correct": 204,
      "n_planned": 231,
      "n_renormalized": 0,
      "n_scorable": 231,
      "n_valid": 231,
      "operational_success": 1.0,
      "ordinal_mae": 0.15935163111560383,
      "price_per_1000_decisions_usd": null,
      "schema_validity": 1.0,
      "schema_validity_strict": 1.0
    }
  },
  "version": "jevbench-v1"
}
