{ "source_zip_sha256": "0ce6ca84e21b70bc47dceea28c5dbf43f917c4c86d771fc11ac9b9fd69799208", "source_report": "compare-db82bc2c6af8", "scope": "Author-written synthetic cases; supplied historical results, not fresh provider calls by Chad. No test of long-term adaptation or benefit from rotation.", "cases": 24, "pair": [ "spark-standard", "wonder-strict" ], "pair_agreement_count": 21, "pair_agreement_fraction": 0.875, "comparison_correct": { "spark-standard": 22, "wonder-strict": 23 }, "calibration_records": [ { "ts": "2026-10-31T09:09:56Z", "config_id": "spark-standard", "n": 24, "accuracy": 0.9583, "false_pass_rate": 0.0, "false_fail_rate": 0.0417 }, { "ts": "2026-10-31T09:12:14Z", "config_id": "wonder-strict", "n": 24, "accuracy": 0.9583, "false_pass_rate": 0.0, "false_fail_rate": 0.0417 } ], "metric_note": "Supplied false_pass_rate uses all cases as denominator, not only expected-fail cases.", "rows": [ { "case_id": "G01", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G02", "expected": "pass", "verdicts": { "spark-standard": "fail", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G03", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G04", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G05", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "fail", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G06", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "fail" } }, { "case_id": "G07", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "fail" } }, { "case_id": "G08", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "pass" } }, { "case_id": "G09", "expected": "fail", "verdicts": { "spark-standard": "pass", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "pass" } }, { "case_id": "G10", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G11", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "fail" } }, { "case_id": "G12", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G13", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G14", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "fail" } }, { "case_id": "G15", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G16", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G17", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "fail" } }, { "case_id": "G18", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G19", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "fail" } }, { "case_id": "G20", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G21", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G22", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } }, { "case_id": "G23", "expected": "fail", "verdicts": { "spark-standard": "fail", "wonder-strict": "fail", "hooman-baseline": "fail", "offline-standard": "fail" } }, { "case_id": "G24", "expected": "pass", "verdicts": { "spark-standard": "pass", "wonder-strict": "pass", "hooman-baseline": "pass", "offline-standard": "pass" } } ] }