{
  "A1": {
    "attempts": 40,
    "answer_correctness": {
      "passed": 28,
      "total": 30,
      "unresolved": 1,
      "lower": 0.9333333333333333,
      "upper": 0.9666666666666667
    },
    "supported_answer_success": {
      "passed": 28,
      "total": 30,
      "unresolved": 0,
      "lower": 0.9333333333333333,
      "upper": 0.9333333333333333
    },
    "abstention_accuracy": {
      "passed": 10,
      "total": 10,
      "unresolved": 0,
      "lower": 1.0,
      "upper": 1.0
    },
    "citation_precision": {
      "passed": 37,
      "total": 38,
      "unresolved": 0,
      "lower": 0.9736842105263158,
      "upper": 0.9736842105263158
    },
    "unresolved_questions": 1,
    "explicit_page_citations": 37,
    "uniquely_quote_mapped_citations": 0,
    "all_semantic_judgments_resolved": false,
    "latency": {
      "n": 40,
      "p50": 4.496676228998695,
      "p95": 6.2484013339853846,
      "max": 8.307981291989563,
      "boundary": "Kingy ask entry through complete returned answer including retrieval, selection and sufficiency check; excludes prior PDF import/index, cold start and warmup."
    }
  },
  "A2": {
    "attempts": 40,
    "answer_correctness": {
      "passed": 28,
      "total": 30,
      "unresolved": 1,
      "lower": 0.9333333333333333,
      "upper": 0.9666666666666667
    },
    "supported_answer_success": {
      "passed": 28,
      "total": 30,
      "unresolved": 0,
      "lower": 0.9333333333333333,
      "upper": 0.9333333333333333
    },
    "abstention_accuracy": {
      "passed": 10,
      "total": 10,
      "unresolved": 0,
      "lower": 1.0,
      "upper": 1.0
    },
    "citation_precision": {
      "passed": 37,
      "total": 38,
      "unresolved": 0,
      "lower": 0.9736842105263158,
      "upper": 0.9736842105263158
    },
    "unresolved_questions": 1,
    "explicit_page_citations": 37,
    "uniquely_quote_mapped_citations": 0,
    "all_semantic_judgments_resolved": false,
    "latency": {
      "n": 40,
      "p50": 2.6608580625033937,
      "p95": 4.6863986249954905,
      "max": 4.918830040987814,
      "boundary": "Kingy ask entry through complete returned answer including retrieval, selection and sufficiency check; excludes prior PDF import/index, cold start and warmup."
    }
  },
  "A3": {
    "attempts": 40,
    "answer_correctness": {
      "passed": 28,
      "total": 30,
      "unresolved": 1,
      "lower": 0.9333333333333333,
      "upper": 0.9666666666666667
    },
    "supported_answer_success": {
      "passed": 28,
      "total": 30,
      "unresolved": 0,
      "lower": 0.9333333333333333,
      "upper": 0.9333333333333333
    },
    "abstention_accuracy": {
      "passed": 10,
      "total": 10,
      "unresolved": 0,
      "lower": 1.0,
      "upper": 1.0
    },
    "citation_precision": {
      "passed": 37,
      "total": 38,
      "unresolved": 0,
      "lower": 0.9736842105263158,
      "upper": 0.9736842105263158
    },
    "unresolved_questions": 1,
    "explicit_page_citations": 37,
    "uniquely_quote_mapped_citations": 0,
    "all_semantic_judgments_resolved": false,
    "latency": {
      "n": 40,
      "p50": 2.68153027050721,
      "p95": 4.550453417003155,
      "max": 4.601461290993029,
      "boundary": "Kingy ask entry through complete returned answer including retrieval, selection and sufficiency check; excludes prior PDF import/index, cold start and warmup."
    }
  },
  "B1": {
    "attempts": 40,
    "answer_correctness": {
      "passed": 16,
      "total": 30,
      "unresolved": 6,
      "lower": 0.5333333333333333,
      "upper": 0.7333333333333333
    },
    "supported_answer_success": {
      "passed": 16,
      "total": 30,
      "unresolved": 2,
      "lower": 0.5333333333333333,
      "upper": 0.6
    },
    "abstention_accuracy": {
      "passed": 9,
      "total": 10,
      "unresolved": 1,
      "lower": 0.9,
      "upper": 1.0
    },
    "citation_precision": {
      "passed": 35,
      "total": 40,
      "unresolved": 1,
      "lower": 0.875,
      "upper": 0.9
    },
    "unresolved_questions": 7,
    "explicit_page_citations": 0,
    "uniquely_quote_mapped_citations": 35,
    "all_semantic_judgments_resolved": false,
    "latency": {
      "n": 40,
      "p50": 13.6965,
      "p95": 20.771,
      "max": 26.497,
      "boundary": "Native app submission to documented logger final-answer event; includes native preprocessing/retrieval/embedding/inference; excludes later title generation and automation/export."
    }
  },
  "B2-partial": {
    "attempts": 7,
    "answer_correctness": {
      "passed": 4,
      "total": 6,
      "unresolved": 1,
      "lower": 0.6666666666666666,
      "upper": 0.8333333333333334
    },
    "supported_answer_success": {
      "passed": 4,
      "total": 6,
      "unresolved": 0,
      "lower": 0.6666666666666666,
      "upper": 0.6666666666666666
    },
    "abstention_accuracy": {
      "passed": 1,
      "total": 1,
      "unresolved": 0,
      "lower": 1.0,
      "upper": 1.0
    },
    "citation_precision": {
      "passed": 8,
      "total": 9,
      "unresolved": 0,
      "lower": 0.8888888888888888,
      "upper": 0.8888888888888888
    },
    "unresolved_questions": 1,
    "explicit_page_citations": 0,
    "uniquely_quote_mapped_citations": 8,
    "all_semantic_judgments_resolved": false,
    "latency": {
      "n": 7,
      "p50": 10.908,
      "p95": 36.418,
      "max": 36.418,
      "boundary": "Native app submission to documented logger final-answer event; includes native preprocessing/retrieval/embedding/inference; excludes later title generation and automation/export."
    }
  }
}