[ { "run_dir": "data/a3f7f0d5", "provider": "claude", "model": "sonnet", "commit": "8b67a88d73b2594570fc21150705283de884620b", "started_at": "2026-10-04T06:34:08+00:00", "finalized_at": "2026-10-04T07:06:07+00:00", "report_score": "3.5/10", "report_grade": "Poor", "files_read": 2803, "source_files": 2803, "totals": { "violationCount": 1752, "complianceCount": 580, "severity": { "critical": 786, "major": 847, "minor": 118 }, "violationsPer100Files": 62.5 }, "requirement_matched": { "overall": { "n": 2740, "tp": 1289, "fn": 126, "fp": 188, "tn": 1137, "tpr": 0.911, "fpr": 0.1419, "score": 0.7691, "mean_of_categories": 0.756 }, "categories": { "cmdi": { "n": 251, "tp": 111, "fn": 15, "fp": 24, "tn": 101, "tpr": 0.881, "fpr": 0.192, "score": 0.689 }, "crypto": { "n": 246, "tp": 130, "fn": 0, "fp": 26, "tn": 90, "tpr": 1.0, "fpr": 0.2241, "score": 0.7759 }, "hash": { "n": 236, "tp": 96, "fn": 33, "fp": 3, "tn": 104, "tpr": 0.7442, "fpr": 0.028, "score": 0.7161 }, "ldapi": { "n": 59, "tp": 24, "fn": 3, "fp": 10, "tn": 22, "tpr": 0.8889, "fpr": 0.3125, "score": 0.5764 }, "pathtraver": { "n": 268, "tp": 120, "fn": 13, "fp": 21, "tn": 114, "tpr": 0.9023, "fpr": 0.1556, "score": 0.7467 }, "securecookie": { "n": 67, "tp": 36, "fn": 0, "fp": 0, "tn": 31, "tpr": 1.0, "fpr": 0.0, "score": 1.0 }, "sqli": { "n": 504, "tp": 256, "fn": 16, "fp": 38, "tn": 194, "tpr": 0.9412, "fpr": 0.1638, "score": 0.7774 }, "trustbound": { "n": 126, "tp": 57, "fn": 26, "fp": 8, "tn": 35, "tpr": 0.6867, "fpr": 0.186, "score": 0.5007 }, "weakrand": { "n": 493, "tp": 217, "fn": 1, "fp": 25, "tn": 250, "tpr": 0.9954, "fpr": 0.0909, "score": 0.9045 }, "xpathi": { "n": 35, "tp": 15, "fn": 0, "fp": 3, "tn": 17, "tpr": 1.0, "fpr": 0.15, "score": 0.85 }, "xss": { "n": 455, "tp": 227, "fn": 19, "fp": 30, "tn": 179, "tpr": 0.9228, "fpr": 0.1435, "score": 0.7792 } } }, "any_finding": { "overall": { "n": 2740, "tp": 1306, "fn": 109, "fp": 276, "tn": 1049, "tpr": 0.923, "fpr": 0.2083, "score": 0.7147, "mean_of_categories": 0.6988 }, "categories": { "cmdi": { "n": 251, "tp": 119, "fn": 7, "fp": 24, "tn": 101, "tpr": 0.9444, "fpr": 0.192, "score": 0.7524 }, "crypto": { "n": 246, "tp": 130, "fn": 0, "fp": 113, "tn": 3, "tpr": 1.0, "fpr": 0.9741, "score": 0.0259 }, "hash": { "n": 236, "tp": 96, "fn": 33, "fp": 3, "tn": 104, "tpr": 0.7442, "fpr": 0.028, "score": 0.7161 }, "ldapi": { "n": 59, "tp": 24, "fn": 3, "fp": 10, "tn": 22, "tpr": 0.8889, "fpr": 0.3125, "score": 0.5764 }, "pathtraver": { "n": 268, "tp": 127, "fn": 6, "fp": 21, "tn": 114, "tpr": 0.9549, "fpr": 0.1556, "score": 0.7993 }, "securecookie": { "n": 67, "tp": 36, "fn": 0, "fp": 0, "tn": 31, "tpr": 1.0, "fpr": 0.0, "score": 1.0 }, "sqli": { "n": 504, "tp": 256, "fn": 16, "fp": 38, "tn": 194, "tpr": 0.9412, "fpr": 0.1638, "score": 0.7774 }, "trustbound": { "n": 126, "tp": 57, "fn": 26, "fp": 8, "tn": 35, "tpr": 0.6867, "fpr": 0.186, "score": 0.5007 }, "weakrand": { "n": 493, "tp": 217, "fn": 1, "fp": 26, "tn": 249, "tpr": 0.9954, "fpr": 0.0945, "score": 0.9009 }, "xpathi": { "n": 35, "tp": 15, "fn": 0, "fp": 3, "tn": 17, "tpr": 1.0, "fpr": 0.15, "score": 0.85 }, "xss": { "n": 455, "tp": 229, "fn": 17, "fp": 30, "tn": 179, "tpr": 0.9309, "fpr": 0.1435, "score": 0.7874 } } } }, { "run_dir": "data/c63548b4", "provider": "codex", "model": "gpt-6-sol", "commit": "8b67a88d73b2594570fc21150705283de884620b", "started_at": "2026-10-05T05:24:47+00:00", "finalized_at": "2026-10-05T05:45:53+00:00", "report_score": "4.4/10", "report_grade": "Poor", "files_read": 2768, "source_files": 2803, "totals": { "violationCount": 2436, "complianceCount": 1201, "severity": { "critical": 139, "major": 191, "minor": 2050 }, "violationsPer100Files": 88.0 }, "requirement_matched": { "overall": { "n": 2740, "tp": 1172, "fn": 243, "fp": 202, "tn": 1123, "tpr": 0.8283, "fpr": 0.1525, "score": 0.6758, "mean_of_categories": 0.6864 }, "categories": { "cmdi": { "n": 251, "tp": 96, "fn": 30, "fp": 22, "tn": 103, "tpr": 0.7619, "fpr": 0.176, "score": 0.5859 }, "crypto": { "n": 246, "tp": 124, "fn": 6, "fp": 9, "tn": 107, "tpr": 0.9538, "fpr": 0.0776, "score": 0.8763 }, "hash": { "n": 236, "tp": 100, "fn": 29, "fp": 2, "tn": 105, "tpr": 0.7752, "fpr": 0.0187, "score": 0.7565 }, "ldapi": { "n": 59, "tp": 25, "fn": 2, "fp": 1, "tn": 31, "tpr": 0.9259, "fpr": 0.0312, "score": 0.8947 }, "pathtraver": { "n": 268, "tp": 101, "fn": 32, "fp": 13, "tn": 122, "tpr": 0.7594, "fpr": 0.0963, "score": 0.6631 }, "securecookie": { "n": 67, "tp": 19, "fn": 17, "fp": 0, "tn": 31, "tpr": 0.5278, "fpr": 0.0, "score": 0.5278 }, "sqli": { "n": 504, "tp": 219, "fn": 53, "fp": 39, "tn": 193, "tpr": 0.8051, "fpr": 0.1681, "score": 0.637 }, "trustbound": { "n": 126, "tp": 36, "fn": 47, "fp": 4, "tn": 39, "tpr": 0.4337, "fpr": 0.093, "score": 0.3407 }, "weakrand": { "n": 493, "tp": 208, "fn": 10, "fp": 78, "tn": 197, "tpr": 0.9541, "fpr": 0.2836, "score": 0.6705 }, "xpathi": { "n": 35, "tp": 13, "fn": 2, "fp": 1, "tn": 19, "tpr": 0.8667, "fpr": 0.05, "score": 0.8167 }, "xss": { "n": 455, "tp": 231, "fn": 15, "fp": 33, "tn": 176, "tpr": 0.939, "fpr": 0.1579, "score": 0.7811 } } }, "any_finding": { "overall": { "n": 2740, "tp": 1194, "fn": 221, "fp": 432, "tn": 893, "tpr": 0.8438, "fpr": 0.326, "score": 0.5178, "mean_of_categories": 0.5747 }, "categories": { "cmdi": { "n": 251, "tp": 102, "fn": 24, "fp": 22, "tn": 103, "tpr": 0.8095, "fpr": 0.176, "score": 0.6335 }, "crypto": { "n": 246, "tp": 129, "fn": 1, "fp": 105, "tn": 11, "tpr": 0.9923, "fpr": 0.9052, "score": 0.0871 }, "hash": { "n": 236, "tp": 101, "fn": 28, "fp": 21, "tn": 86, "tpr": 0.7829, "fpr": 0.1963, "score": 0.5867 }, "ldapi": { "n": 59, "tp": 25, "fn": 2, "fp": 1, "tn": 31, "tpr": 0.9259, "fpr": 0.0312, "score": 0.8947 }, "pathtraver": { "n": 268, "tp": 108, "fn": 25, "fp": 17, "tn": 118, "tpr": 0.812, "fpr": 0.1259, "score": 0.6861 }, "securecookie": { "n": 67, "tp": 22, "fn": 14, "fp": 0, "tn": 31, "tpr": 0.6111, "fpr": 0.0, "score": 0.6111 }, "sqli": { "n": 504, "tp": 219, "fn": 53, "fp": 39, "tn": 193, "tpr": 0.8051, "fpr": 0.1681, "score": 0.637 }, "trustbound": { "n": 126, "tp": 36, "fn": 47, "fp": 5, "tn": 38, "tpr": 0.4337, "fpr": 0.1163, "score": 0.3175 }, "weakrand": { "n": 493, "tp": 208, "fn": 10, "fp": 188, "tn": 87, "tpr": 0.9541, "fpr": 0.6836, "score": 0.2705 }, "xpathi": { "n": 35, "tp": 13, "fn": 2, "fp": 1, "tn": 19, "tpr": 0.8667, "fpr": 0.05, "score": 0.8167 }, "xss": { "n": 455, "tp": 231, "fn": 15, "fp": 33, "tn": 176, "tpr": 0.939, "fpr": 0.1579, "score": 0.7811 } } } }, { "run_dir": "data/0ecec3e5", "provider": "codex", "model": "gpt-6-luna", "commit": "8b67a88d73b2594570fc21150705283de884620b", "started_at": "2026-10-04T05:24:53+00:00", "finalized_at": "2026-10-04T06:26:43+00:00", "report_score": "4.7/10", "report_grade": "Poor", "files_read": 2538, "source_files": 2803, "totals": { "violationCount": 1334, "complianceCount": 174, "severity": { "critical": 12, "major": 18, "minor": 1304 }, "violationsPer100Files": 52.6 }, "requirement_matched": { "overall": { "n": 2740, "tp": 703, "fn": 712, "fp": 216, "tn": 1109, "tpr": 0.4968, "fpr": 0.163, "score": 0.3338, "mean_of_categories": 0.3247 }, "categories": { "cmdi": { "n": 251, "tp": 43, "fn": 83, "fp": 17, "tn": 108, "tpr": 0.3413, "fpr": 0.136, "score": 0.2053 }, "crypto": { "n": 246, "tp": 72, "fn": 58, "fp": 9, "tn": 107, "tpr": 0.5538, "fpr": 0.0776, "score": 0.4763 }, "hash": { "n": 236, "tp": 48, "fn": 81, "fp": 2, "tn": 105, "tpr": 0.3721, "fpr": 0.0187, "score": 0.3534 }, "ldapi": { "n": 59, "tp": 21, "fn": 6, "fp": 9, "tn": 23, "tpr": 0.7778, "fpr": 0.2812, "score": 0.4965 }, "pathtraver": { "n": 268, "tp": 54, "fn": 79, "fp": 28, "tn": 107, "tpr": 0.406, "fpr": 0.2074, "score": 0.1986 }, "securecookie": { "n": 67, "tp": 5, "fn": 31, "fp": 2, "tn": 29, "tpr": 0.1389, "fpr": 0.0645, "score": 0.0744 }, "sqli": { "n": 504, "tp": 186, "fn": 86, "fp": 78, "tn": 154, "tpr": 0.6838, "fpr": 0.3362, "score": 0.3476 }, "trustbound": { "n": 126, "tp": 2, "fn": 81, "fp": 0, "tn": 43, "tpr": 0.0241, "fpr": 0.0, "score": 0.0241 }, "weakrand": { "n": 493, "tp": 120, "fn": 98, "fp": 21, "tn": 254, "tpr": 0.5505, "fpr": 0.0764, "score": 0.4741 }, "xpathi": { "n": 35, "tp": 13, "fn": 2, "fp": 6, "tn": 14, "tpr": 0.8667, "fpr": 0.3, "score": 0.5667 }, "xss": { "n": 455, "tp": 139, "fn": 107, "fp": 44, "tn": 165, "tpr": 0.565, "fpr": 0.2105, "score": 0.3545 } } }, "any_finding": { "overall": { "n": 2740, "tp": 792, "fn": 623, "fp": 334, "tn": 991, "tpr": 0.5597, "fpr": 0.2521, "score": 0.3076, "mean_of_categories": 0.3222 }, "categories": { "cmdi": { "n": 251, "tp": 57, "fn": 69, "fp": 26, "tn": 99, "tpr": 0.4524, "fpr": 0.208, "score": 0.2444 }, "crypto": { "n": 246, "tp": 81, "fn": 49, "fp": 26, "tn": 90, "tpr": 0.6231, "fpr": 0.2241, "score": 0.3989 }, "hash": { "n": 236, "tp": 51, "fn": 78, "fp": 8, "tn": 99, "tpr": 0.3953, "fpr": 0.0748, "score": 0.3206 }, "ldapi": { "n": 59, "tp": 21, "fn": 6, "fp": 9, "tn": 23, "tpr": 0.7778, "fpr": 0.2812, "score": 0.4965 }, "pathtraver": { "n": 268, "tp": 81, "fn": 52, "fp": 40, "tn": 95, "tpr": 0.609, "fpr": 0.2963, "score": 0.3127 }, "securecookie": { "n": 67, "tp": 8, "fn": 28, "fp": 2, "tn": 29, "tpr": 0.2222, "fpr": 0.0645, "score": 0.1577 }, "sqli": { "n": 504, "tp": 190, "fn": 82, "fp": 84, "tn": 148, "tpr": 0.6985, "fpr": 0.3621, "score": 0.3365 }, "trustbound": { "n": 126, "tp": 4, "fn": 79, "fp": 2, "tn": 41, "tpr": 0.0482, "fpr": 0.0465, "score": 0.0017 }, "weakrand": { "n": 493, "tp": 144, "fn": 74, "fp": 85, "tn": 190, "tpr": 0.6606, "fpr": 0.3091, "score": 0.3515 }, "xpathi": { "n": 35, "tp": 13, "fn": 2, "fp": 6, "tn": 14, "tpr": 0.8667, "fpr": 0.3, "score": 0.5667 }, "xss": { "n": 455, "tp": 142, "fn": 104, "fp": 46, "tn": 163, "tpr": 0.5772, "fpr": 0.2201, "score": 0.3571 } } } }, { "run_dir": "data/ef6db373", "provider": "ollama", "model": "gemma4:26b-mlx", "commit": "8b67a88d73b2594570fc21150705283de884620b", "started_at": "2026-10-04T07:17:08+00:00", "finalized_at": "2026-10-04T09:46:28+00:00", "report_score": "4.4/10", "report_grade": "Poor", "files_read": 2773, "source_files": 2800, "totals": { "violationCount": 2655, "complianceCount": 145, "severity": { "critical": 1686, "major": 954, "minor": 15 }, "violationsPer100Files": 95.7 }, "requirement_matched": { "overall": { "n": 2740, "tp": 1203, "fn": 212, "fp": 867, "tn": 458, "tpr": 0.8502, "fpr": 0.6543, "score": 0.1958, "mean_of_categories": 0.2087 }, "categories": { "cmdi": { "n": 251, "tp": 125, "fn": 1, "fp": 120, "tn": 5, "tpr": 0.9921, "fpr": 0.96, "score": 0.0321 }, "crypto": { "n": 246, "tp": 128, "fn": 2, "fp": 18, "tn": 98, "tpr": 0.9846, "fpr": 0.1552, "score": 0.8294 }, "hash": { "n": 236, "tp": 89, "fn": 40, "fp": 9, "tn": 98, "tpr": 0.6899, "fpr": 0.0841, "score": 0.6058 }, "ldapi": { "n": 59, "tp": 14, "fn": 13, "fp": 21, "tn": 11, "tpr": 0.5185, "fpr": 0.6562, "score": -0.1377 }, "pathtraver": { "n": 268, "tp": 132, "fn": 1, "fp": 135, "tn": 0, "tpr": 0.9925, "fpr": 1.0, "score": -0.0075 }, "securecookie": { "n": 67, "tp": 31, "fn": 5, "fp": 0, "tn": 31, "tpr": 0.8611, "fpr": 0.0, "score": 0.8611 }, "sqli": { "n": 504, "tp": 270, "fn": 2, "fp": 231, "tn": 1, "tpr": 0.9926, "fpr": 0.9957, "score": -0.003 }, "trustbound": { "n": 126, "tp": 3, "fn": 80, "fp": 3, "tn": 40, "tpr": 0.0361, "fpr": 0.0698, "score": -0.0336 }, "weakrand": { "n": 493, "tp": 187, "fn": 31, "fp": 168, "tn": 107, "tpr": 0.8578, "fpr": 0.6109, "score": 0.2469 }, "xpathi": { "n": 35, "tp": 10, "fn": 5, "fp": 19, "tn": 1, "tpr": 0.6667, "fpr": 0.95, "score": -0.2833 }, "xss": { "n": 455, "tp": 214, "fn": 32, "fp": 143, "tn": 66, "tpr": 0.8699, "fpr": 0.6842, "score": 0.1857 } } }, "any_finding": { "overall": { "n": 2740, "tp": 1333, "fn": 82, "fp": 1128, "tn": 197, "tpr": 0.942, "fpr": 0.8513, "score": 0.0907, "mean_of_categories": 0.1408 }, "categories": { "cmdi": { "n": 251, "tp": 126, "fn": 0, "fp": 125, "tn": 0, "tpr": 1.0, "fpr": 1.0, "score": 0.0 }, "crypto": { "n": 246, "tp": 128, "fn": 2, "fp": 72, "tn": 44, "tpr": 0.9846, "fpr": 0.6207, "score": 0.3639 }, "hash": { "n": 236, "tp": 123, "fn": 6, "fp": 88, "tn": 19, "tpr": 0.9535, "fpr": 0.8224, "score": 0.1311 }, "ldapi": { "n": 59, "tp": 26, "fn": 1, "fp": 31, "tn": 1, "tpr": 0.963, "fpr": 0.9688, "score": -0.0058 }, "pathtraver": { "n": 268, "tp": 132, "fn": 1, "fp": 135, "tn": 0, "tpr": 0.9925, "fpr": 1.0, "score": -0.0075 }, "securecookie": { "n": 67, "tp": 36, "fn": 0, "fp": 4, "tn": 27, "tpr": 1.0, "fpr": 0.129, "score": 0.871 }, "sqli": { "n": 504, "tp": 270, "fn": 2, "fp": 231, "tn": 1, "tpr": 0.9926, "fpr": 0.9957, "score": -0.003 }, "trustbound": { "n": 126, "tp": 37, "fn": 46, "fp": 21, "tn": 22, "tpr": 0.4458, "fpr": 0.4884, "score": -0.0426 }, "weakrand": { "n": 493, "tp": 200, "fn": 18, "fp": 233, "tn": 42, "tpr": 0.9174, "fpr": 0.8473, "score": 0.0702 }, "xpathi": { "n": 35, "tp": 15, "fn": 0, "fp": 20, "tn": 0, "tpr": 1.0, "fpr": 1.0, "score": 0.0 }, "xss": { "n": 455, "tp": 240, "fn": 6, "fp": 168, "tn": 41, "tpr": 0.9756, "fpr": 0.8038, "score": 0.1718 } } } }, { "run_dir": "data/085f9175", "provider": "ollama", "model": "qwen3.8:27b-mlx", "commit": "8b67a88d73b2594570fc21150705283de884620b", "started_at": "2026-10-04T09:52:35+00:00", "finalized_at": "2026-10-04T18:43:29+00:00", "report_score": "4.8/10", "report_grade": "Poor", "files_read": 2797, "source_files": 2800, "totals": { "violationCount": 4026, "complianceCount": 1017, "severity": { "critical": 1817, "major": 2043, "minor": 166 }, "violationsPer100Files": 143.9 }, "requirement_matched": { "overall": { "n": 2740, "tp": 1306, "fn": 109, "fp": 953, "tn": 372, "tpr": 0.923, "fpr": 0.7192, "score": 0.2037, "mean_of_categories": 0.2476 }, "categories": { "cmdi": { "n": 251, "tp": 124, "fn": 2, "fp": 116, "tn": 9, "tpr": 0.9841, "fpr": 0.928, "score": 0.0561 }, "crypto": { "n": 246, "tp": 128, "fn": 2, "fp": 30, "tn": 86, "tpr": 0.9846, "fpr": 0.2586, "score": 0.726 }, "hash": { "n": 236, "tp": 89, "fn": 40, "fp": 20, "tn": 87, "tpr": 0.6899, "fpr": 0.1869, "score": 0.503 }, "ldapi": { "n": 59, "tp": 27, "fn": 0, "fp": 32, "tn": 0, "tpr": 1.0, "fpr": 1.0, "score": 0.0 }, "pathtraver": { "n": 268, "tp": 133, "fn": 0, "fp": 109, "tn": 26, "tpr": 1.0, "fpr": 0.8074, "score": 0.1926 }, "securecookie": { "n": 67, "tp": 36, "fn": 0, "fp": 8, "tn": 23, "tpr": 1.0, "fpr": 0.2581, "score": 0.7419 }, "sqli": { "n": 504, "tp": 271, "fn": 1, "fp": 219, "tn": 13, "tpr": 0.9963, "fpr": 0.944, "score": 0.0524 }, "trustbound": { "n": 126, "tp": 20, "fn": 63, "fp": 9, "tn": 34, "tpr": 0.241, "fpr": 0.2093, "score": 0.0317 }, "weakrand": { "n": 493, "tp": 218, "fn": 0, "fp": 253, "tn": 22, "tpr": 1.0, "fpr": 0.92, "score": 0.08 }, "xpathi": { "n": 35, "tp": 15, "fn": 0, "fp": 20, "tn": 0, "tpr": 1.0, "fpr": 1.0, "score": 0.0 }, "xss": { "n": 455, "tp": 245, "fn": 1, "fp": 137, "tn": 72, "tpr": 0.9959, "fpr": 0.6555, "score": 0.3404 } } }, "any_finding": { "overall": { "n": 2740, "tp": 1353, "fn": 62, "fp": 1152, "tn": 173, "tpr": 0.9562, "fpr": 0.8694, "score": 0.0867, "mean_of_categories": 0.1309 }, "categories": { "cmdi": { "n": 251, "tp": 124, "fn": 2, "fp": 116, "tn": 9, "tpr": 0.9841, "fpr": 0.928, "score": 0.0561 }, "crypto": { "n": 246, "tp": 130, "fn": 0, "fp": 116, "tn": 0, "tpr": 1.0, "fpr": 1.0, "score": 0.0 }, "hash": { "n": 236, "tp": 128, "fn": 1, "fp": 96, "tn": 11, "tpr": 0.9922, "fpr": 0.8972, "score": 0.0951 }, "ldapi": { "n": 59, "tp": 27, "fn": 0, "fp": 32, "tn": 0, "tpr": 1.0, "fpr": 1.0, "score": 0.0 }, "pathtraver": { "n": 268, "tp": 133, "fn": 0, "fp": 116, "tn": 19, "tpr": 1.0, "fpr": 0.8593, "score": 0.1407 }, "securecookie": { "n": 67, "tp": 36, "fn": 0, "fp": 8, "tn": 23, "tpr": 1.0, "fpr": 0.2581, "score": 0.7419 }, "sqli": { "n": 504, "tp": 271, "fn": 1, "fp": 220, "tn": 12, "tpr": 0.9963, "fpr": 0.9483, "score": 0.048 }, "trustbound": { "n": 126, "tp": 25, "fn": 58, "fp": 11, "tn": 32, "tpr": 0.3012, "fpr": 0.2558, "score": 0.0454 }, "weakrand": { "n": 493, "tp": 218, "fn": 0, "fp": 268, "tn": 7, "tpr": 1.0, "fpr": 0.9745, "score": 0.0255 }, "xpathi": { "n": 35, "tp": 15, "fn": 0, "fp": 20, "tn": 0, "tpr": 1.0, "fpr": 1.0, "score": 0.0 }, "xss": { "n": 455, "tp": 246, "fn": 0, "fp": 149, "tn": 60, "tpr": 1.0, "fpr": 0.7129, "score": 0.2871 } } } } ]