{"abstract":"A generous outlier judge inflates the dive score.","category":"Sports scoring and tiebreakers","checks":8,"contract":"Diving dive score. scores are judge marks as strings from 0 to 10 in half points; any other mark returns \"invalid mark <s>\". A 5-judge panel drops the single highest and lowest marks, a 7-judge panel the two highest and two lowest; any other panel size returns \"invalid panel\". The three remaining marks are summed and multiplied by the degree of difficulty dd (a decimal string); return the exact result with two decimals.","contract_signature":"scores, dd","evaluation_group":"w2-sports-scoring-diving-judges-trim","failed_approach":"Trimming only the high end lets a harsh outlier deflate the score.","family":"w2-sports-scoring-diving-judges-trim-trim-both-ends","id":"FA-84251","implementations":{"attempt":{"sha256":"6e5d27408d7c87994a8ad0e15245a1170b31e9988fd9b7504498f6d42fdee877","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\nfrom fractions import Fraction\nN = 1\nobservations = []\ndef solve(scores, dd):\n    marks = []\n    for s in scores:\n        v = Fraction(s)\n        if v < 0 or v > 10 or (v * 2).denominator != 1:\n            return 'invalid mark ' + s\n        marks.append(v)\n    if len(marks) == 5:\n        drop = 1\n    elif len(marks) == 7:\n        drop = 2\n    else:\n        return 'invalid panel'\n    kept = sorted(marks)[:len(marks) - drop]\n    total = sum(kept) * Fraction(dd)\n    return '%.2f' % float(total)\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ndef run(args):\n    try:\n        return solve(*args)\n    except Exception as exc:\n        return 'raised ' + type(exc).__name__\ncases = [[('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends',\n   (['8.0', '2.0', '4.5', '3.5', '0.5', '2.5', '6.5'], '1.6'),\n   '16.80'),\n  ('variant scenario 1', (['4.0', '4.5', '0.0', '9.0', '7.0', '1.5'], '1.6'), 'invalid panel'),\n  ('variant scenario 2', (['8.5', '8.5', '1.5', '1.0', '4.0'], '1.6'), '22.40')],\n [('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends',\n   (['10.0', '8.5', '3.5', '2.0', '3.0', '2.5', '8.0'], '2.8'),\n   '40.60'),\n  ('variant scenario 1', (['1.5', '6.5', '10.0', '8.5', '0.0'], '3.1'), '51.15'),\n  ('variant scenario 2', (['7.3', '3.5', '5.0', '6.5', '7.5', '2.0'], '3.1'), 'invalid mark 7.3')],\n [('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends',\n   (['10.0', '2.0', '5.5', '2.0', '9.5', '5.5', '9.5'], '3.1'),\n   '63.55'),\n  ('variant scenario 1', (['-1.0', '5.5', '3.5', '5.0', '8.5', '9.5'], '1.6'), 'invalid mark -1.0'),\n  ('variant scenario 2', (['1.0', '1.5', '6.5', '8.0', '7.0', '7.0', '4.0'], '1.6'), '28.00')],\n [('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends', (['4.0', '0.5', '2.5', '1.5', '0.0'], '3.1'), '13.95'),\n  ('regression: trim both ends', (['8.5', '9.5', '3.0', '3.5', '8.5'], '1.6'), '32.80'),\n  ('variant scenario 1', (['1.0', '7.5', '1.5', '1.0', '0.0'], '3.1'), '10.85'),\n  ('variant scenario 2', (['8.0', '2.0', '3.0', '7.5', '7.0', '5.0'], '3.1'), 'invalid panel')],\n [('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends', (['8.5', '6.5', '9.5', '5.5', '7.5'], '2.0'), '45.00'),\n  ('variant scenario 1', (['2.5', '3.0', '8.5', '7.5', '4.5', '2.0'], '3.1'), 'invalid panel'),\n  ('variant scenario 2', (['10.5', '4.5', '0.5', '3.5', '9.5'], '3.1'), 'invalid mark 10.5')]]\nfor label, args, expected in cases[N - 1]:\n    check(label, run(args), expected)\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"},"broken":{"sha256":"1b340dabfbcc320d937f95d76867a3264bdf05c4a75371cecfaeb7826fd60a92","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\nfrom fractions import Fraction\nN = 1\nobservations = []\ndef solve(scores, dd):\n    marks = []\n    for s in scores:\n        v = Fraction(s)\n        if v < 0 or v > 10 or (v * 2).denominator != 1:\n            return 'invalid mark ' + s\n        marks.append(v)\n    if len(marks) == 5:\n        drop = 1\n    elif len(marks) == 7:\n        drop = 2\n    else:\n        return 'invalid panel'\n    kept = sorted(marks)[drop:]\n    total = sum(kept) * Fraction(dd)\n    return '%.2f' % float(total)\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ndef run(args):\n    try:\n        return solve(*args)\n    except Exception as exc:\n        return 'raised ' + type(exc).__name__\ncases = [[('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends',\n   (['8.0', '2.0', '4.5', '3.5', '0.5', '2.5', '6.5'], '1.6'),\n   '16.80'),\n  ('variant scenario 1', (['4.0', '4.5', '0.0', '9.0', '7.0', '1.5'], '1.6'), 'invalid panel'),\n  ('variant scenario 2', (['8.5', '8.5', '1.5', '1.0', '4.0'], '1.6'), '22.40')],\n [('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends',\n   (['10.0', '8.5', '3.5', '2.0', '3.0', '2.5', '8.0'], '2.8'),\n   '40.60'),\n  ('variant scenario 1', (['1.5', '6.5', '10.0', '8.5', '0.0'], '3.1'), '51.15'),\n  ('variant scenario 2', (['7.3', '3.5', '5.0', '6.5', '7.5', '2.0'], '3.1'), 'invalid mark 7.3')],\n [('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends',\n   (['10.0', '2.0', '5.5', '2.0', '9.5', '5.5', '9.5'], '3.1'),\n   '63.55'),\n  ('variant scenario 1', (['-1.0', '5.5', '3.5', '5.0', '8.5', '9.5'], '1.6'), 'invalid mark -1.0'),\n  ('variant scenario 2', (['1.0', '1.5', '6.5', '8.0', '7.0', '7.0', '4.0'], '1.6'), '28.00')],\n [('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends', (['4.0', '0.5', '2.5', '1.5', '0.0'], '3.1'), '13.95'),\n  ('regression: trim both ends', (['8.5', '9.5', '3.0', '3.5', '8.5'], '1.6'), '32.80'),\n  ('variant scenario 1', (['1.0', '7.5', '1.5', '1.0', '0.0'], '3.1'), '10.85'),\n  ('variant scenario 2', (['8.0', '2.0', '3.0', '7.5', '7.0', '5.0'], '3.1'), 'invalid panel')],\n [('control five-judge panel', (['7.0', '7.5', '6.5', '8.0', '7.0'], '2.0'), '43.00'),\n  ('control seven-judge panel',\n   (['8.0', '8.5', '9.0', '7.5', '8.0', '8.5', '6.0'], '3.1'),\n   '75.95'),\n  ('boundary perfect tens', (['10.0', '10.0', '10.0', '10.0', '10.0'], '3.4'), '102.00'),\n  ('boundary non-half mark', (['7.3', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid mark 7.3'),\n  ('boundary six judges', (['7.0', '7.0', '7.0', '7.0', '7.0', '7.0'], '2.0'), 'invalid panel'),\n  ('regression: trim both ends', (['8.5', '6.5', '9.5', '5.5', '7.5'], '2.0'), '45.00'),\n  ('variant scenario 1', (['2.5', '3.0', '8.5', '7.5', '4.5', '2.0'], '3.1'), 'invalid panel'),\n  ('variant scenario 2', (['10.5', '4.5', '0.5', '3.5', '9.5'], '3.1'), 'invalid mark 10.5')]]\nfor label, args, expected in cases[N - 1]:\n    check(label, run(args), expected)\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"}},"limitations":"Stipulated, bounded toy contract stated in the contract field; not a claim of conformance with any governing body rulebook or operator house rules. This reproducer isolates one failure mechanism. Results cover the supplied fixtures. Variants within a family share a test contract and should remain grouped when constructing evaluation splits. Related mechanisms with a shared evaluation_group must also remain together; these controlled models are not independent production incidents.","method":"Deterministic executable model with adversarial boundary fixtures.","provenance":{"created_by":"Failure Map","dependencies":"Python standard library","family":"w2-sports-scoring-diving-judges-trim-trim-both-ends","generated_at":"2026-09-29T14:50:29.144485+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"Meet management systems compute dive scores from judge panels of different sizes.","root_cause":"The slice removes marks from the low end only.","sha256":"f6aad3e64378566ade6c230fe70ba74b995fcf0c8343652d9cf41aae160ea5bc","title":"Only the low marks are trimmed · case 01","variant":1,"variant_policy":"Five numbered records share a model and may reuse boundary fixtures.","verified":true,"visibility":"public","verification":{"attempt":{"elapsed_ms":41.664,"exit_code":1,"observations":[{"actual":"56.00","check":"control five-judge panel","expected":"43.00","passed":false},{"actual":"117.80","check":"control seven-judge panel","expected":"75.95","passed":false},{"actual":"136.00","check":"boundary perfect tens","expected":"102.00","passed":false},{"actual":"invalid mark 7.3","check":"boundary non-half mark","expected":"invalid mark 7.3","passed":true},{"actual":"invalid panel","check":"boundary six judges","expected":"invalid panel","passed":true},{"actual":"20.80","check":"regression: trim both ends","expected":"16.80","passed":false},{"actual":"invalid panel","check":"variant scenario 1","expected":"invalid panel","passed":true},{"actual":"24.00","check":"variant scenario 2","expected":"22.40","passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"control five-judge panel\", \"actual\": \"56.00\", \"expected\": \"43.00\", \"passed\": false}, {\"check\": \"control seven-judge panel\", \"actual\": \"117.80\", \"expected\": \"75.95\", \"passed\": false}, {\"check\": \"boundary perfect tens\", \"actual\": \"136.00\", \"expected\": \"102.00\", \"passed\": false}, {\"check\": \"boundary non-half mark\", \"actual\": \"invalid mark 7.3\", \"expected\": \"invalid mark 7.3\", \"passed\": true}, {\"check\": \"boundary six judges\", \"actual\": \"invalid panel\", \"expected\": \"invalid panel\", \"passed\": true}, {\"check\": \"regression: trim both ends\", \"actual\": \"20.80\", \"expected\": \"16.80\", \"passed\": false}, {\"check\": \"variant scenario 1\", \"actual\": \"invalid panel\", \"expected\": \"invalid panel\", \"passed\": true}, {\"check\": \"variant scenario 2\", \"actual\": \"24.00\", \"expected\": \"22.40\", \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":42.756,"exit_code":1,"observations":[{"actual":"59.00","check":"control five-judge panel","expected":"43.00","passed":false},{"actual":"130.20","check":"control seven-judge panel","expected":"75.95","passed":false},{"actual":"136.00","check":"boundary perfect tens","expected":"102.00","passed":false},{"actual":"invalid mark 7.3","check":"boundary non-half mark","expected":"invalid mark 7.3","passed":true},{"actual":"invalid panel","check":"boundary six judges","expected":"invalid panel","passed":true},{"actual":"40.00","check":"regression: trim both ends","expected":"16.80","passed":false},{"actual":"invalid panel","check":"variant scenario 1","expected":"invalid panel","passed":true},{"actual":"36.00","check":"variant scenario 2","expected":"22.40","passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"control five-judge panel\", \"actual\": \"59.00\", \"expected\": \"43.00\", \"passed\": false}, {\"check\": \"control seven-judge panel\", \"actual\": \"130.20\", \"expected\": \"75.95\", \"passed\": false}, {\"check\": \"boundary perfect tens\", \"actual\": \"136.00\", \"expected\": \"102.00\", \"passed\": false}, {\"check\": \"boundary non-half mark\", \"actual\": \"invalid mark 7.3\", \"expected\": \"invalid mark 7.3\", \"passed\": true}, {\"check\": \"boundary six judges\", \"actual\": \"invalid panel\", \"expected\": \"invalid panel\", \"passed\": true}, {\"check\": \"regression: trim both ends\", \"actual\": \"40.00\", \"expected\": \"16.80\", \"passed\": false}, {\"check\": \"variant scenario 1\", \"actual\": \"invalid panel\", \"expected\": \"invalid panel\", \"passed\": true}, {\"check\": \"variant scenario 2\", \"actual\": \"36.00\", \"expected\": \"22.40\", \"passed\": false}], \"passed\": false}\n"}},"member_only":{"stages":["fixed"],"fields":["implementations.fixed","verification.fixed","harness","repair"],"note":"The verified repair, its recorded checks, the repair description, and the scoring harness are available to members."}}