{"abstract":"Small arms get understated variance and overconfident t statistics.","category":"Experiment statistics","checks":8,"contract":"a is control, b treatment. With sample variances (divisor n - 1), t = (mean_b - mean_a) / sqrt(va/na + vb/nb) and Welch-Satterthwaite df = (va/na + vb/nb)^2 / ((va/na)^2/(na-1) + (vb/nb)^2/(nb-1)). Fewer than two values in an arm or zero total variance -> None. Return [round(t, 6), round(df, 6)].","evaluation_group":"w2-experiment-statistics-welch-t","failed_approach":"Dividing by the pooled na + nb - 2 mixes a pooled-variance idea into Welch.","family":"w2-experiment-statistics-welch-t-bessel-correction","id":"FA-74391","implementations":{"attempt":{"sha256":"0c3acea939dbb4b1dd0c396628eb9d2864bd20dd8e6c3724add6ac397e266a71","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\nimport math\nN = 1\nobservations = []\ndef solve(a, b):\n    na, nb = len(a), len(b)\n    if na < 2 or nb < 2:\n        return None\n    ma, mb = sum(a) / na, sum(b) / nb\n    va = sum((x - ma) ** 2 for x in a) / (na + nb - 2)\n    vb = sum((x - mb) ** 2 for x in b) / (na + nb - 2)\n    sa, sb = va / na, vb / nb\n    if sa + sb == 0:\n        return None\n    t = (mb - ma) / math.sqrt(sa + sb)\n    df = (sa + sb) ** 2 / (sa ** 2 / (na - 1) + sb ** 2 / (nb - 1))\n    return [round(t, 6), round(df, 6)]\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\nfixtures = [[('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('metric sample 1', [[0, 18, 6, 6], [3, 7, 11, 17, 25, 22]], [1.290726, 7.219744]),\n  ('metric sample 2', [[12, 18, 10, 0, 10], [15, 23, 29, 2, 16]], [1.302114, 6.806789]),\n  ('metric sample 3', [[5, 3], [21, 5, 12, 23]], [2.622967, 3.321892])],\n [('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 4', [[6, 14, 12, 14, 7, 11, 3], [17, 29, 25, 22, 10]], [3.004687, 5.927117]),\n  ('metric sample 6', [[13, 17, 16, 14, 0, 13], [10, 0, 6, 6, 0, 16, 5, 16]], [-1.428489, 10.999617]),\n  ('metric sample 7', [[0, 9, 16, 8, 15, 5, 3], [29, 4, 20, 26, 11, 20]], [2.332551, 8.238859])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 11', [[6, 10], [16, 12, 20, 6, 18]], [2.007859, 4.050223]),\n  ('metric sample 12', [[7, 0], [27, 17, 26, 19, 20, 24, 1]], [3.236139, 3.199156]),\n  ('metric sample 13', [[7, 13, 5, 4, 12], [6, 24, 6, 27, 4, 8, 3, 17, 7, 17]], [1.122702, 12.999998])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 16',\n   [[13, 7, 4, 9, 13, 12], [20, 21, 17, 13, 14, 25, 13, 11, 16, 14, 6]],\n   [2.66816, 13.725637]),\n  ('metric sample 17', [[10, 4, 0, 14], [6, 17, 1, 13, 11]], [0.622825, 6.572986]),\n  ('metric sample 18', [[18, 12, 1, 1], [12, 28, 6, 18, 8, 4, 15, 27, 24]], [1.497776, 6.245264])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 21', [[0, 8, 15, 10], [28, 21, 11, 23, 28, 28]], [3.601238, 6.91205]),\n  ('metric sample 22', [[1, 5, 15], [29, 28, 6, 25, 5, 12]], [1.705196, 6.118881]),\n  ('metric sample 25', [[17, 3], [0, 10, 29, 29, 25, 3, 18]], [0.751104, 1.981932])]]\nfor label, args, expected in fixtures[N - 1]:\n    check(label, solve(*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":"7e8bb67bb68a6378d5fbdc418be8e23ed417f00180344d3873a6602f5332e01a","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\nimport math\nN = 1\nobservations = []\ndef solve(a, b):\n    na, nb = len(a), len(b)\n    if na < 2 or nb < 2:\n        return None\n    ma, mb = sum(a) / na, sum(b) / nb\n    va = sum((x - ma) ** 2 for x in a) / na\n    vb = sum((x - mb) ** 2 for x in b) / nb\n    sa, sb = va / na, vb / nb\n    if sa + sb == 0:\n        return None\n    t = (mb - ma) / math.sqrt(sa + sb)\n    df = (sa + sb) ** 2 / (sa ** 2 / (na - 1) + sb ** 2 / (nb - 1))\n    return [round(t, 6), round(df, 6)]\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\nfixtures = [[('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('metric sample 1', [[0, 18, 6, 6], [3, 7, 11, 17, 25, 22]], [1.290726, 7.219744]),\n  ('metric sample 2', [[12, 18, 10, 0, 10], [15, 23, 29, 2, 16]], [1.302114, 6.806789]),\n  ('metric sample 3', [[5, 3], [21, 5, 12, 23]], [2.622967, 3.321892])],\n [('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 4', [[6, 14, 12, 14, 7, 11, 3], [17, 29, 25, 22, 10]], [3.004687, 5.927117]),\n  ('metric sample 6', [[13, 17, 16, 14, 0, 13], [10, 0, 6, 6, 0, 16, 5, 16]], [-1.428489, 10.999617]),\n  ('metric sample 7', [[0, 9, 16, 8, 15, 5, 3], [29, 4, 20, 26, 11, 20]], [2.332551, 8.238859])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 11', [[6, 10], [16, 12, 20, 6, 18]], [2.007859, 4.050223]),\n  ('metric sample 12', [[7, 0], [27, 17, 26, 19, 20, 24, 1]], [3.236139, 3.199156]),\n  ('metric sample 13', [[7, 13, 5, 4, 12], [6, 24, 6, 27, 4, 8, 3, 17, 7, 17]], [1.122702, 12.999998])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 16',\n   [[13, 7, 4, 9, 13, 12], [20, 21, 17, 13, 14, 25, 13, 11, 16, 14, 6]],\n   [2.66816, 13.725637]),\n  ('metric sample 17', [[10, 4, 0, 14], [6, 17, 1, 13, 11]], [0.622825, 6.572986]),\n  ('metric sample 18', [[18, 12, 1, 1], [12, 28, 6, 18, 8, 4, 15, 27, 24]], [1.497776, 6.245264])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 21', [[0, 8, 15, 10], [28, 21, 11, 23, 28, 28]], [3.601238, 6.91205]),\n  ('metric sample 22', [[1, 5, 15], [29, 28, 6, 25, 5, 12]], [1.705196, 6.118881]),\n  ('metric sample 25', [[17, 3], [0, 10, 29, 29, 25, 3, 18]], [0.751104, 1.981932])]]\nfor label, args, expected in fixtures[N - 1]:\n    check(label, solve(*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":"55cc5b2be0520abe67645ab700fa8a85381675fe15916f10152acceea5261f4d","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\nimport math\nN = 1\nobservations = []\ndef solve(a, b):\n    na, nb = len(a), len(b)\n    if na < 2 or nb < 2:\n        return None\n    ma, mb = sum(a) / na, sum(b) / nb\n    va = sum((x - ma) ** 2 for x in a) / (na - 1)\n    vb = sum((x - mb) ** 2 for x in b) / (nb - 1)\n    sa, sb = va / na, vb / nb\n    if sa + sb == 0:\n        return None\n    t = (mb - ma) / math.sqrt(sa + sb)\n    df = (sa + sb) ** 2 / (sa ** 2 / (na - 1) + sb ** 2 / (nb - 1))\n    return [round(t, 6), round(df, 6)]\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\nfixtures = [[('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('metric sample 1', [[0, 18, 6, 6], [3, 7, 11, 17, 25, 22]], [1.290726, 7.219744]),\n  ('metric sample 2', [[12, 18, 10, 0, 10], [15, 23, 29, 2, 16]], [1.302114, 6.806789]),\n  ('metric sample 3', [[5, 3], [21, 5, 12, 23]], [2.622967, 3.321892])],\n [('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 4', [[6, 14, 12, 14, 7, 11, 3], [17, 29, 25, 22, 10]], [3.004687, 5.927117]),\n  ('metric sample 6', [[13, 17, 16, 14, 0, 13], [10, 0, 6, 6, 0, 16, 5, 16]], [-1.428489, 10.999617]),\n  ('metric sample 7', [[0, 9, 16, 8, 15, 5, 3], [29, 4, 20, 26, 11, 20]], [2.332551, 8.238859])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 11', [[6, 10], [16, 12, 20, 6, 18]], [2.007859, 4.050223]),\n  ('metric sample 12', [[7, 0], [27, 17, 26, 19, 20, 24, 1]], [3.236139, 3.199156]),\n  ('metric sample 13', [[7, 13, 5, 4, 12], [6, 24, 6, 27, 4, 8, 3, 17, 7, 17]], [1.122702, 12.999998])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('equal arms give zero t', [[1, 2, 3], [1, 2, 3]], [0.0, 4.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 16',\n   [[13, 7, 4, 9, 13, 12], [20, 21, 17, 13, 14, 25, 13, 11, 16, 14, 6]],\n   [2.66816, 13.725637]),\n  ('metric sample 17', [[10, 4, 0, 14], [6, 17, 1, 13, 11]], [0.622825, 6.572986]),\n  ('metric sample 18', [[18, 12, 1, 1], [12, 28, 6, 18, 8, 4, 15, 27, 24]], [1.497776, 6.245264])],\n [('unequal sizes and variances', [[1, 2, 3, 4], [2, 4, 6, 8, 10, 12]], [2.713602, 6.594671]),\n  ('two-point arms', [[0, 2], [5, 9]], [2.683282, 1.470588]),\n  ('one arm constant', [[3, 3, 3], [1, 5, 9]], [0.866025, 2.0]),\n  ('negative effect', [[10, 12, 14, 16], [1, 3, 2]], [-7.778175, 4.075472]),\n  ('single observation arm', [[1], [2, 3]], None),\n  ('metric sample 21', [[0, 8, 15, 10], [28, 21, 11, 23, 28, 28]], [3.601238, 6.91205]),\n  ('metric sample 22', [[1, 5, 15], [29, 28, 6, 25, 5, 12]], [1.705196, 6.118881]),\n  ('metric sample 25', [[17, 3], [0, 10, 29, 29, 25, 3, 18]], [0.751104, 1.981932])]]\nfor label, args, expected in fixtures[N - 1]:\n    check(label, solve(*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":"A deterministic toy experiment-analysis model with a stipulated contract; results are rounded and are not a substitute for a validated statistics package. 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-experiment-statistics-welch-t-bessel-correction","generated_at":"2026-09-29T14:48:56.475596+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"Online experiment readouts drive launch decisions; a silent formula slip flips conclusions.","repair":"Divide the squared deviations by n - 1 in each arm.","root_cause":"Variances divide by n instead of n - 1.","sha256":"f0e10d481af07c29a6f04bfe1c0e8045aa74763493f77a44896d9cdeb4c29474","title":"Welch unequal-variance t statistic: Arm variances use the population divisor · case 01","variant":1,"variant_policy":"Five numbered records share a model and may reuse boundary fixtures.","verification":{"attempt":{"elapsed_ms":37.883,"exit_code":1,"observations":[{"actual":[3.54146,6.013767],"check":"unequal sizes and variances","expected":[2.713602,6.594671],"passed":false},{"actual":[3.794733,1.470588],"check":"two-point arms","expected":[2.683282,1.470588],"passed":false},{"actual":[1.224745,2.0],"check":"one arm constant","expected":[0.866025,2.0],"passed":false},{"actual":[0.0,4.0],"check":"equal arms give zero t","expected":[0.0,4.0],"passed":true},{"actual":[-10.332701,3.753247],"check":"negative effect","expected":[-7.778175,4.075472],"passed":false},{"actual":[1.841149,7.963945],"check":"metric sample 1","expected":[1.290726,7.219744],"passed":false},{"actual":[1.841468,6.806789],"check":"metric sample 2","expected":[1.302114,6.806789],"passed":false},{"actual":[3.08516,3.112643],"check":"metric sample 3","expected":[2.622967,3.321892],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"unequal sizes and variances\", \"actual\": [3.54146, 6.013767], \"expected\": [2.713602, 6.594671], \"passed\": false}, {\"check\": \"two-point arms\", \"actual\": [3.794733, 1.470588], \"expected\": [2.683282, 1.470588], \"passed\": false}, {\"check\": \"one arm constant\", \"actual\": [1.224745, 2.0], \"expected\": [0.866025, 2.0], \"passed\": false}, {\"check\": \"equal arms give zero t\", \"actual\": [0.0, 4.0], \"expected\": [0.0, 4.0], \"passed\": true}, {\"check\": \"negative effect\", \"actual\": [-10.332701, 3.753247], \"expected\": [-7.778175, 4.075472], \"passed\": false}, {\"check\": \"metric sample 1\", \"actual\": [1.841149, 7.963945], \"expected\": [1.290726, 7.219744], \"passed\": false}, {\"check\": \"metric sample 2\", \"actual\": [1.841468, 6.806789], \"expected\": [1.302114, 6.806789], \"passed\": false}, {\"check\": \"metric sample 3\", \"actual\": [3.08516, 3.112643], \"expected\": [2.622967, 3.321892], \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":38.264,"exit_code":1,"observations":[{"actual":[2.995381,6.45827],"check":"unequal sizes and variances","expected":[2.713602,6.594671],"passed":false},{"actual":[3.794733,1.470588],"check":"two-point arms","expected":[2.683282,1.470588],"passed":false},{"actual":[1.06066,2.0],"check":"one arm constant","expected":[0.866025,2.0],"passed":false},{"actual":[0.0,4.0],"check":"equal arms give zero t","expected":[0.0,4.0],"passed":true},{"actual":[-9.065797,3.973126],"check":"negative effect","expected":[-7.778175,4.075472],"passed":false},{"actual":[1.453265,7.439647],"check":"metric sample 1","expected":[1.290726,7.219744],"passed":false},{"actual":[1.455808,6.806789],"check":"metric sample 2","expected":[1.302114,6.806789],"passed":false},{"actual":[3.05656,3.220158],"check":"metric sample 3","expected":[2.622967,3.321892],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"unequal sizes and variances\", \"actual\": [2.995381, 6.45827], \"expected\": [2.713602, 6.594671], \"passed\": false}, {\"check\": \"two-point arms\", \"actual\": [3.794733, 1.470588], \"expected\": [2.683282, 1.470588], \"passed\": false}, {\"check\": \"one arm constant\", \"actual\": [1.06066, 2.0], \"expected\": [0.866025, 2.0], \"passed\": false}, {\"check\": \"equal arms give zero t\", \"actual\": [0.0, 4.0], \"expected\": [0.0, 4.0], \"passed\": true}, {\"check\": \"negative effect\", \"actual\": [-9.065797, 3.973126], \"expected\": [-7.778175, 4.075472], \"passed\": false}, {\"check\": \"metric sample 1\", \"actual\": [1.453265, 7.439647], \"expected\": [1.290726, 7.219744], \"passed\": false}, {\"check\": \"metric sample 2\", \"actual\": [1.455808, 6.806789], \"expected\": [1.302114, 6.806789], \"passed\": false}, {\"check\": \"metric sample 3\", \"actual\": [3.05656, 3.220158], \"expected\": [2.622967, 3.321892], \"passed\": false}], \"passed\": false}\n"},"fixed":{"elapsed_ms":38.024,"exit_code":0,"observations":[{"actual":[2.713602,6.594671],"check":"unequal sizes and variances","expected":[2.713602,6.594671],"passed":true},{"actual":[2.683282,1.470588],"check":"two-point arms","expected":[2.683282,1.470588],"passed":true},{"actual":[0.866025,2.0],"check":"one arm constant","expected":[0.866025,2.0],"passed":true},{"actual":[0.0,4.0],"check":"equal arms give zero t","expected":[0.0,4.0],"passed":true},{"actual":[-7.778175,4.075472],"check":"negative effect","expected":[-7.778175,4.075472],"passed":true},{"actual":[1.290726,7.219744],"check":"metric sample 1","expected":[1.290726,7.219744],"passed":true},{"actual":[1.302114,6.806789],"check":"metric sample 2","expected":[1.302114,6.806789],"passed":true},{"actual":[2.622967,3.321892],"check":"metric sample 3","expected":[2.622967,3.321892],"passed":true}],"passed":true,"stderr":"","stdout":"{\"observations\": [{\"check\": \"unequal sizes and variances\", \"actual\": [2.713602, 6.594671], \"expected\": [2.713602, 6.594671], \"passed\": true}, {\"check\": \"two-point arms\", \"actual\": [2.683282, 1.470588], \"expected\": [2.683282, 1.470588], \"passed\": true}, {\"check\": \"one arm constant\", \"actual\": [0.866025, 2.0], \"expected\": [0.866025, 2.0], \"passed\": true}, {\"check\": \"equal arms give zero t\", \"actual\": [0.0, 4.0], \"expected\": [0.0, 4.0], \"passed\": true}, {\"check\": \"negative effect\", \"actual\": [-7.778175, 4.075472], \"expected\": [-7.778175, 4.075472], \"passed\": true}, {\"check\": \"metric sample 1\", \"actual\": [1.290726, 7.219744], \"expected\": [1.290726, 7.219744], \"passed\": true}, {\"check\": \"metric sample 2\", \"actual\": [1.302114, 6.806789], \"expected\": [1.302114, 6.806789], \"passed\": true}, {\"check\": \"metric sample 3\", \"actual\": [2.622967, 3.321892], \"expected\": [2.622967, 3.321892], \"passed\": true}], \"passed\": true}\n"}},"verified":true,"visibility":"public"}