{"abstract":"Dive scores are a third of the expected value.","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.","evaluation_group":"w2-sports-scoring-diving-judges-trim","failed_approach":"Averaging all marks and scaling by three ignores the trimming.","family":"w2-sports-scoring-diving-judges-trim-sum-versus-average","id":"FA-84261","implementations":{"attempt":{"sha256":"2315cbf166a9a7533062689eacfa2235a2c2ec3e8af80991c90ce013c6564734","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:len(marks) - drop]\n    total = sum(marks) * Fraction(dd) * 3 / len(marks)\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: sum versus average', (['2.0', '7.5', '4.0', '4.5', '2.0'], '3.7'), '38.85'),\n  ('variant scenario 1', (['7.5', '2.5', '8.0', '0.0', '4.5', '5.5', '6.0'], '3.4'), '54.40'),\n  ('variant scenario 2', (['5.5', '7.0', '9.0', '2.5', '0.0', '1.5', '7.0'], '3.4'), '51.00')],\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: sum versus average', (['8.5', '4.5', '10.0', '10.0', '1.0'], '2.0'), '46.00'),\n  ('variant scenario 1', (['2.5', '5.0', '5.5', '2.5', '1.5', '6.5'], '1.6'), 'invalid panel'),\n  ('variant scenario 2', (['7.5', '8.5', '0.0', '7.0', '5.5', '6.0', '6.5'], '3.7'), '72.15')],\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: sum versus average', (['6.5', '2.0', '8.5', '0.0', '8.5'], '3.1'), '52.70'),\n  ('variant scenario 1', (['1.5', '8.5', '2.0', '4.5', '8.5'], '3.1'), '46.50'),\n  ('variant scenario 2', (['6.0', '0.5', '9.0', '1.0', '7.5', '3.5', '4.0'], '3.4'), '45.90')],\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: sum versus average', (['4.0', '4.0', '3.5', '5.5', '3.5'], '3.1'), '35.65'),\n  ('variant scenario 1', (['5.0', '10.0', '6.0', '9.0', '0.0', '5.0'], '2.0'), 'invalid panel'),\n  ('variant scenario 2', (['11.0', '3.0', '5.5', '5.5', '7.0'], '3.4'), 'invalid mark 11.0')],\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: sum versus average',\n   (['0.0', '5.5', '3.0', '7.5', '7.5', '10.0', '5.5'], '3.7'),\n   '68.45'),\n  ('variant scenario 1', (['6.5', '2.5', '7.0', '6.5', '7.5', '4.0'], '3.1'), 'invalid panel'),\n  ('variant scenario 2', (['9.0', '7.5', '7.5', '0.5', '1.5'], '3.7'), '61.05')]]\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":"dfb7f106877f7bce37af45ae58bb2fb32380f1758ae11d926a0118f4ae63e3a6","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:len(marks) - drop]\n    total = sum(kept) / len(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: sum versus average', (['2.0', '7.5', '4.0', '4.5', '2.0'], '3.7'), '38.85'),\n  ('variant scenario 1', (['7.5', '2.5', '8.0', '0.0', '4.5', '5.5', '6.0'], '3.4'), '54.40'),\n  ('variant scenario 2', (['5.5', '7.0', '9.0', '2.5', '0.0', '1.5', '7.0'], '3.4'), '51.00')],\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: sum versus average', (['8.5', '4.5', '10.0', '10.0', '1.0'], '2.0'), '46.00'),\n  ('variant scenario 1', (['2.5', '5.0', '5.5', '2.5', '1.5', '6.5'], '1.6'), 'invalid panel'),\n  ('variant scenario 2', (['7.5', '8.5', '0.0', '7.0', '5.5', '6.0', '6.5'], '3.7'), '72.15')],\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: sum versus average', (['6.5', '2.0', '8.5', '0.0', '8.5'], '3.1'), '52.70'),\n  ('variant scenario 1', (['1.5', '8.5', '2.0', '4.5', '8.5'], '3.1'), '46.50'),\n  ('variant scenario 2', (['6.0', '0.5', '9.0', '1.0', '7.5', '3.5', '4.0'], '3.4'), '45.90')],\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: sum versus average', (['4.0', '4.0', '3.5', '5.5', '3.5'], '3.1'), '35.65'),\n  ('variant scenario 1', (['5.0', '10.0', '6.0', '9.0', '0.0', '5.0'], '2.0'), 'invalid panel'),\n  ('variant scenario 2', (['11.0', '3.0', '5.5', '5.5', '7.0'], '3.4'), 'invalid mark 11.0')],\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: sum versus average',\n   (['0.0', '5.5', '3.0', '7.5', '7.5', '10.0', '5.5'], '3.7'),\n   '68.45'),\n  ('variant scenario 1', (['6.5', '2.5', '7.0', '6.5', '7.5', '4.0'], '3.1'), 'invalid panel'),\n  ('variant scenario 2', (['9.0', '7.5', '7.5', '0.5', '1.5'], '3.7'), '61.05')]]\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"},"fixed":{"sha256":"b27a5b0d774f12dc2534dfa639455aa18f32d2d4c9fb2a8691c7b9e33fbbb1ab","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: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: sum versus average', (['2.0', '7.5', '4.0', '4.5', '2.0'], '3.7'), '38.85'),\n  ('variant scenario 1', (['7.5', '2.5', '8.0', '0.0', '4.5', '5.5', '6.0'], '3.4'), '54.40'),\n  ('variant scenario 2', (['5.5', '7.0', '9.0', '2.5', '0.0', '1.5', '7.0'], '3.4'), '51.00')],\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: sum versus average', (['8.5', '4.5', '10.0', '10.0', '1.0'], '2.0'), '46.00'),\n  ('variant scenario 1', (['2.5', '5.0', '5.5', '2.5', '1.5', '6.5'], '1.6'), 'invalid panel'),\n  ('variant scenario 2', (['7.5', '8.5', '0.0', '7.0', '5.5', '6.0', '6.5'], '3.7'), '72.15')],\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: sum versus average', (['6.5', '2.0', '8.5', '0.0', '8.5'], '3.1'), '52.70'),\n  ('variant scenario 1', (['1.5', '8.5', '2.0', '4.5', '8.5'], '3.1'), '46.50'),\n  ('variant scenario 2', (['6.0', '0.5', '9.0', '1.0', '7.5', '3.5', '4.0'], '3.4'), '45.90')],\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: sum versus average', (['4.0', '4.0', '3.5', '5.5', '3.5'], '3.1'), '35.65'),\n  ('variant scenario 1', (['5.0', '10.0', '6.0', '9.0', '0.0', '5.0'], '2.0'), 'invalid panel'),\n  ('variant scenario 2', (['11.0', '3.0', '5.5', '5.5', '7.0'], '3.4'), 'invalid mark 11.0')],\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: sum versus average',\n   (['0.0', '5.5', '3.0', '7.5', '7.5', '10.0', '5.5'], '3.7'),\n   '68.45'),\n  ('variant scenario 1', (['6.5', '2.5', '7.0', '6.5', '7.5', '4.0'], '3.1'), 'invalid panel'),\n  ('variant scenario 2', (['9.0', '7.5', '7.5', '0.5', '1.5'], '3.7'), '61.05')]]\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-sum-versus-average","generated_at":"2026-09-29T14:50:29.178769+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.","repair":"Sum the three kept marks and multiply by the degree of difficulty.","root_cause":"The kept marks are averaged instead of summed.","sha256":"c236dddcf00485bb4ffcd8644562305a9d134ea952a5f0199c15456422b6c88b","title":"Trimmed marks averaged before multiplying by difficulty · case 01","variant":1,"variant_policy":"Five numbered records share a model and may reuse boundary fixtures.","verification":{"attempt":{"elapsed_ms":45.036,"exit_code":1,"observations":[{"actual":"43.20","check":"control five-judge panel","expected":"43.00","passed":false},{"actual":"73.74","check":"control seven-judge panel","expected":"75.95","passed":false},{"actual":"102.00","check":"boundary perfect tens","expected":"102.00","passed":true},{"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":"44.40","check":"regression: sum versus average","expected":"38.85","passed":false},{"actual":"49.54","check":"variant scenario 1","expected":"54.40","passed":false},{"actual":"47.36","check":"variant scenario 2","expected":"51.00","passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"control five-judge panel\", \"actual\": \"43.20\", \"expected\": \"43.00\", \"passed\": false}, {\"check\": \"control seven-judge panel\", \"actual\": \"73.74\", \"expected\": \"75.95\", \"passed\": false}, {\"check\": \"boundary perfect tens\", \"actual\": \"102.00\", \"expected\": \"102.00\", \"passed\": true}, {\"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: sum versus average\", \"actual\": \"44.40\", \"expected\": \"38.85\", \"passed\": false}, {\"check\": \"variant scenario 1\", \"actual\": \"49.54\", \"expected\": \"54.40\", \"passed\": false}, {\"check\": \"variant scenario 2\", \"actual\": \"47.36\", \"expected\": \"51.00\", \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":43.406,"exit_code":1,"observations":[{"actual":"14.33","check":"control five-judge panel","expected":"43.00","passed":false},{"actual":"25.32","check":"control seven-judge panel","expected":"75.95","passed":false},{"actual":"34.00","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":"12.95","check":"regression: sum versus average","expected":"38.85","passed":false},{"actual":"18.13","check":"variant scenario 1","expected":"54.40","passed":false},{"actual":"17.00","check":"variant scenario 2","expected":"51.00","passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"control five-judge panel\", \"actual\": \"14.33\", \"expected\": \"43.00\", \"passed\": false}, {\"check\": \"control seven-judge panel\", \"actual\": \"25.32\", \"expected\": \"75.95\", \"passed\": false}, {\"check\": \"boundary perfect tens\", \"actual\": \"34.00\", \"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: sum versus average\", \"actual\": \"12.95\", \"expected\": \"38.85\", \"passed\": false}, {\"check\": \"variant scenario 1\", \"actual\": \"18.13\", \"expected\": \"54.40\", \"passed\": false}, {\"check\": \"variant scenario 2\", \"actual\": \"17.00\", \"expected\": \"51.00\", \"passed\": false}], \"passed\": false}\n"},"fixed":{"elapsed_ms":42.09,"exit_code":0,"observations":[{"actual":"43.00","check":"control five-judge panel","expected":"43.00","passed":true},{"actual":"75.95","check":"control seven-judge panel","expected":"75.95","passed":true},{"actual":"102.00","check":"boundary perfect tens","expected":"102.00","passed":true},{"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":"38.85","check":"regression: sum versus average","expected":"38.85","passed":true},{"actual":"54.40","check":"variant scenario 1","expected":"54.40","passed":true},{"actual":"51.00","check":"variant scenario 2","expected":"51.00","passed":true}],"passed":true,"stderr":"","stdout":"{\"observations\": [{\"check\": \"control five-judge panel\", \"actual\": \"43.00\", \"expected\": \"43.00\", \"passed\": true}, {\"check\": \"control seven-judge panel\", \"actual\": \"75.95\", \"expected\": \"75.95\", \"passed\": true}, {\"check\": \"boundary perfect tens\", \"actual\": \"102.00\", \"expected\": \"102.00\", \"passed\": true}, {\"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: sum versus average\", \"actual\": \"38.85\", \"expected\": \"38.85\", \"passed\": true}, {\"check\": \"variant scenario 1\", \"actual\": \"54.40\", \"expected\": \"54.40\", \"passed\": true}, {\"check\": \"variant scenario 2\", \"actual\": \"51.00\", \"expected\": \"51.00\", \"passed\": true}], \"passed\": true}\n"}},"verified":true,"visibility":"public"}