{
  "source_revision": "9788ecc5526b32da9fa9b9b38964586060677c77",
  "new_api_calls": 0,
  "binary_choice_count": 12,
  "max_absolute_formula_gap": 0.01000000000000012,
  "binary_choices": [
    {
      "case": "order-ambiguous-False-False-0",
      "question": "intent",
      "top_probability": 0.96,
      "api_confidence": 0.92,
      "absolute_formula_gap": 1.1102230246251565e-16
    },
    {
      "case": "order-ambiguous-False-False-1",
      "question": "intent",
      "top_probability": 0.96,
      "api_confidence": 0.92,
      "absolute_formula_gap": 1.1102230246251565e-16
    },
    {
      "case": "order-ambiguous-False-False-2",
      "question": "intent",
      "top_probability": 0.97,
      "api_confidence": 0.94,
      "absolute_formula_gap": 0.0
    },
    {
      "case": "order-ambiguous-True-False-0",
      "question": "intent",
      "top_probability": 0.95,
      "api_confidence": 0.89,
      "absolute_formula_gap": 0.009999999999999898
    },
    {
      "case": "order-ambiguous-True-False-1",
      "question": "intent",
      "top_probability": 0.96,
      "api_confidence": 0.93,
      "absolute_formula_gap": 0.01000000000000012
    },
    {
      "case": "order-ambiguous-True-False-2",
      "question": "intent",
      "top_probability": 0.95,
      "api_confidence": 0.9,
      "absolute_formula_gap": 1.1102230246251565e-16
    },
    {
      "case": "order-clear-False-False-0",
      "question": "intent",
      "top_probability": 1.0,
      "api_confidence": 1.0,
      "absolute_formula_gap": 0.0
    },
    {
      "case": "order-clear-False-False-1",
      "question": "intent",
      "top_probability": 1.0,
      "api_confidence": 1.0,
      "absolute_formula_gap": 0.0
    },
    {
      "case": "order-clear-False-False-2",
      "question": "intent",
      "top_probability": 1.0,
      "api_confidence": 1.0,
      "absolute_formula_gap": 0.0
    },
    {
      "case": "order-clear-True-False-0",
      "question": "intent",
      "top_probability": 1.0,
      "api_confidence": 1.0,
      "absolute_formula_gap": 0.0
    },
    {
      "case": "order-clear-True-False-1",
      "question": "intent",
      "top_probability": 1.0,
      "api_confidence": 1.0,
      "absolute_formula_gap": 0.0
    },
    {
      "case": "order-clear-True-False-2",
      "question": "intent",
      "top_probability": 1.0,
      "api_confidence": 1.0,
      "absolute_formula_gap": 0.0
    }
  ],
  "ece_boundary_diagnostic": {
    "scores": [
      0.0,
      1.0
    ],
    "labels": [
      1,
      1
    ],
    "original_open_left_bins": 0.0,
    "zero_inclusive_first_bin": 0.5
  },
  "scope": "Saved-answer inspection and isolated metric boundary check; no OpenHands calibration claim."
}
