{ "benchmark": "REDACT (Vats et al., EMNLP 2026 Industry Track, arXiv 2606.19881)", "split": "pii_benchmark_sample1000.json (locked detector split, 1,000 records, 40 per language)", "split_sha256": "754f562ce9c3c5b7b663f1ba6127c38a31d93f5631d38364341cb727936234c6", "dataset_terms": "https://github.com/guneeshvats/REDACT-PII-Benchmark/blob/main/DATASET_TERMS.md", "connector": "2.57.0", "commit": "0ca409b", "date": "2026-11-03", "harness": "connecteur/bench/redact (passer.mjs, noter.mjs, comparer.mjs, types.mjs)", "routes": { "text": { "route": "vu", "fiches": 1000, "erreurs": 0, "manquantes": 0, "imbriques": 445, "directs": { "total": 17103, "touches": 16903, "caches": 14967, "touches_pct": 98.8, "caches_pct": 87.5, "intacts": 200 }, "niveaux": { "LOW": { "total": 5043, "touches": 4024, "caches": 2979, "touches_pct": 79.8, "caches_pct": 59.1 }, "MEDIUM": { "total": 14761, "touches": 14465, "caches": 13154, "touches_pct": 98, "caches_pct": 89.1 }, "HIGH": { "total": 3624, "touches": 3065, "caches": 2083, "touches_pct": 84.6, "caches_pct": 57.5 } }, "dates_de_naissance": { "total": 570, "lisibles": 347, "caches": 172, "lisibles_pct": 60.9, "caches_pct": 30.2 }, "texte_ordinaire_code_pct": { "AR": 76.9, "CS": 73.7, "DA": 67.1, "DE": 78.5, "EN": 24.6, "ES": 65.6, "FI": 78.1, "FR": 10.7, "FR_CA": 9, "HE": 65.7, "HI": 51.1, "HU": 73.9, "IT": 65.2, "JA": 74.3, "KO": 80.8, "NL": 61.9, "NO": 72.6, "PT_BR": 68.5, "PT_EU": 65.5, "RU": 83.5, "SV": 73, "TH": 79.7, "TR": 85.6, "ZH_CN": 77.4, "ZH_TW": 61.7 }, "decodage_exact": { "texte": 372, "fichier": 765, "sur": 1000 }, "officiel": { "partial": { "tp": 6881, "fp": 36691, "fn": 17318, "precision": 0.1579, "recall": 0.2844, "f1": 0.2031, "macro_f1": 0.0632, "per_type": { "Account_Statements": { "tp": 0, "fp": 0, "fn": 75, "precision": 0, "recall": 0, "f1": 0 }, "Address_Personal": { "tp": 51, "fp": 46, "fn": 470, "precision": 0.5258, "recall": 0.0979, "f1": 0.165 }, "Address_Work": { "tp": 0, "fp": 0, "fn": 185, "precision": 0, "recall": 0, "f1": 0 }, "Age": { "tp": 0, "fp": 0, "fn": 115, "precision": 0, "recall": 0, "f1": 0 }, "Allergy_Information": { "tp": 0, "fp": 0, "fn": 85, "precision": 0, "recall": 0, "f1": 0 }, "Building_Badge_Card_Number": { "tp": 0, "fp": 0, "fn": 43, "precision": 0, "recall": 0, "f1": 0 }, "Business_Title": { "tp": 0, "fp": 0, "fn": 537, "precision": 0, "recall": 0, "f1": 0 }, "Citizenship_Status": { "tp": 0, "fp": 0, "fn": 62, "precision": 0, "recall": 0, "f1": 0 }, "City": { "tp": 0, "fp": 0, "fn": 954, "precision": 0, "recall": 0, "f1": 0 }, "Compensation_and_Salary": { "tp": 0, "fp": 0, "fn": 219, "precision": 0, "recall": 0, "f1": 0 }, "Country_of_Residence": { "tp": 0, "fp": 0, "fn": 32, "precision": 0, "recall": 0, "f1": 0 }, "Credit_Card_Numbers": { "tp": 12, "fp": 19, "fn": 120, "precision": 0.3871, "recall": 0.0909, "f1": 0.1472 }, "Crime": { "tp": 0, "fp": 0, "fn": 114, "precision": 0, "recall": 0, "f1": 0 }, "Customer_Reference_Number": { "tp": 1450, "fp": 3655, "fn": 341, "precision": 0.284, "recall": 0.8096, "f1": 0.4205 }, "Date_Time": { "tp": 0, "fp": 0, "fn": 1422, "precision": 0, "recall": 0, "f1": 0 }, "Date_of_Birth": { "tp": 51, "fp": 0, "fn": 535, "precision": 1, "recall": 0.087, "f1": 0.1601 }, "Disciplinary_Action": { "tp": 0, "fp": 0, "fn": 18, "precision": 0, "recall": 0, "f1": 0 }, "Driving_License_Number": { "tp": 0, "fp": 0, "fn": 41, "precision": 0, "recall": 0, "f1": 0 }, "Emergency_Contact_Details": { "tp": 0, "fp": 0, "fn": 24, "precision": 0, "recall": 0, "f1": 0 }, "Employee_ID_Number": { "tp": 0, "fp": 0, "fn": 560, "precision": 0, "recall": 0, "f1": 0 }, "First_Given_Name": { "tp": 280, "fp": 516, "fn": 2939, "precision": 0.3518, "recall": 0.087, "f1": 0.1395 }, "Full_Name": { "tp": 2700, "fp": 3312, "fn": 1458, "precision": 0.4491, "recall": 0.6494, "f1": 0.531 }, "Gender": { "tp": 0, "fp": 0, "fn": 130, "precision": 0, "recall": 0, "f1": 0 }, "Geolocation_Data": { "tp": 0, "fp": 0, "fn": 55, "precision": 0, "recall": 0, "f1": 0 }, "Last_Family_Name": { "tp": 578, "fp": 24712, "fn": 2690, "precision": 0.0229, "recall": 0.1769, "f1": 0.0405 }, "Location": { "tp": 0, "fp": 0, "fn": 121, "precision": 0, "recall": 0, "f1": 0 }, "Marital_Status": { "tp": 0, "fp": 0, "fn": 126, "precision": 0, "recall": 0, "f1": 0 }, "Medical_Information": { "tp": 0, "fp": 0, "fn": 317, "precision": 0, "recall": 0, "f1": 0 }, "National_Identification_Number": { "tp": 12, "fp": 91, "fn": 595, "precision": 0.1165, "recall": 0.0198, "f1": 0.0338 }, "Nationality": { "tp": 0, "fp": 0, "fn": 219, "precision": 0, "recall": 0, "f1": 0 }, "Org_Name": { "tp": 257, "fp": 3274, "fn": 708, "precision": 0.0728, "recall": 0.2663, "f1": 0.1143 }, "PEP_Status": { "tp": 0, "fp": 0, "fn": 46, "precision": 0, "recall": 0, "f1": 0 }, "Passport_Number": { "tp": 0, "fp": 0, "fn": 126, "precision": 0, "recall": 0, "f1": 0 }, "Password": { "tp": 0, "fp": 0, "fn": 39, "precision": 0, "recall": 0, "f1": 0 }, "Performance_Assessment": { "tp": 0, "fp": 0, "fn": 37, "precision": 0, "recall": 0, "f1": 0 }, "Personal_Email_Address": { "tp": 0, "fp": 0, "fn": 452, "precision": 0, "recall": 0, "f1": 0 }, "Place_of_Birth": { "tp": 0, "fp": 0, "fn": 38, "precision": 0, "recall": 0, "f1": 0 }, "Political_Party": { "tp": 0, "fp": 0, "fn": 45, "precision": 0, "recall": 0, "f1": 0 }, "Preferred_Name": { "tp": 0, "fp": 0, "fn": 87, "precision": 0, "recall": 0, "f1": 0 }, "Professional_Background": { "tp": 0, "fp": 0, "fn": 33, "precision": 0, "recall": 0, "f1": 0 }, "Religion": { "tp": 0, "fp": 0, "fn": 67, "precision": 0, "recall": 0, "f1": 0 }, "Sex_Orientation": { "tp": 0, "fp": 0, "fn": 65, "precision": 0, "recall": 0, "f1": 0 }, "Sickness_Day_Records": { "tp": 0, "fp": 0, "fn": 36, "precision": 0, "recall": 0, "f1": 0 }, "Social_Media_Identifiers": { "tp": 9, "fp": 86, "fn": 172, "precision": 0.0947, "recall": 0.0497, "f1": 0.0652 }, "State": { "tp": 0, "fp": 0, "fn": 111, "precision": 0, "recall": 0, "f1": 0 }, "Static_IP_Address": { "tp": 0, "fp": 0, "fn": 103, "precision": 0, "recall": 0, "f1": 0 }, "Tax_Reference_Number": { "tp": 0, "fp": 12, "fn": 38, "precision": 0, "recall": 0, "f1": 0 }, "Telephone_Numbers_Personal": { "tp": 490, "fp": 482, "fn": 126, "precision": 0.5041, "recall": 0.7955, "f1": 0.6171 }, "Telephone_Numbers_Work": { "tp": 0, "fp": 0, "fn": 307, "precision": 0, "recall": 0, "f1": 0 }, "Trade_Union_Membership": { "tp": 0, "fp": 0, "fn": 35, "precision": 0, "recall": 0, "f1": 0 }, "Work_Email_Address": { "tp": 991, "fp": 486, "fn": 45, "precision": 0.671, "recall": 0.9566, "f1": 0.7887 } }, "per_language": { "AR": { "tp": 192, "fp": 796, "fn": 775, "precision": 0.1943, "recall": 0.1986, "f1": 0.1964 }, "CS": { "tp": 316, "fp": 1761, "fn": 690, "precision": 0.1521, "recall": 0.3141, "f1": 0.205 }, "DA": { "tp": 320, "fp": 1658, "fn": 762, "precision": 0.1618, "recall": 0.2957, "f1": 0.2092 }, "DE": { "tp": 341, "fp": 2729, "fn": 691, "precision": 0.1111, "recall": 0.3304, "f1": 0.1663 }, "EN": { "tp": 378, "fp": 1908, "fn": 717, "precision": 0.1654, "recall": 0.3452, "f1": 0.2236 }, "ES": { "tp": 393, "fp": 2230, "fn": 768, "precision": 0.1498, "recall": 0.3385, "f1": 0.2077 }, "FI": { "tp": 304, "fp": 1940, "fn": 674, "precision": 0.1355, "recall": 0.3108, "f1": 0.1887 }, "FR": { "tp": 348, "fp": 592, "fn": 535, "precision": 0.3702, "recall": 0.3941, "f1": 0.3818 }, "FR_CA": { "tp": 336, "fp": 547, "fn": 595, "precision": 0.3805, "recall": 0.3609, "f1": 0.3705 }, "HE": { "tp": 188, "fp": 723, "fn": 742, "precision": 0.2064, "recall": 0.2022, "f1": 0.2042 }, "HI": { "tp": 273, "fp": 1105, "fn": 640, "precision": 0.1981, "recall": 0.299, "f1": 0.2383 }, "HU": { "tp": 283, "fp": 1398, "fn": 665, "precision": 0.1684, "recall": 0.2985, "f1": 0.2153 }, "IT": { "tp": 335, "fp": 2046, "fn": 701, "precision": 0.1407, "recall": 0.3234, "f1": 0.1961 }, "JA": { "tp": 142, "fp": 887, "fn": 760, "precision": 0.138, "recall": 0.1574, "f1": 0.1471 }, "KO": { "tp": 162, "fp": 1030, "fn": 671, "precision": 0.1359, "recall": 0.1945, "f1": 0.16 }, "NL": { "tp": 365, "fp": 1667, "fn": 744, "precision": 0.1796, "recall": 0.3291, "f1": 0.2324 }, "NO": { "tp": 262, "fp": 1808, "fn": 633, "precision": 0.1266, "recall": 0.2927, "f1": 0.1767 }, "PT_BR": { "tp": 425, "fp": 2227, "fn": 840, "precision": 0.1603, "recall": 0.336, "f1": 0.217 }, "PT_EU": { "tp": 267, "fp": 2074, "fn": 594, "precision": 0.1141, "recall": 0.3101, "f1": 0.1668 }, "RU": { "tp": 199, "fp": 1290, "fn": 559, "precision": 0.1336, "recall": 0.2625, "f1": 0.1771 }, "SV": { "tp": 311, "fp": 1721, "fn": 709, "precision": 0.1531, "recall": 0.3049, "f1": 0.2038 }, "TH": { "tp": 120, "fp": 669, "fn": 534, "precision": 0.1521, "recall": 0.1835, "f1": 0.1663 }, "TR": { "tp": 397, "fp": 2205, "fn": 845, "precision": 0.1526, "recall": 0.3196, "f1": 0.2066 }, "ZH_CN": { "tp": 123, "fp": 913, "fn": 812, "precision": 0.1187, "recall": 0.1316, "f1": 0.1248 }, "ZH_TW": { "tp": 101, "fp": 767, "fn": 662, "precision": 0.1164, "recall": 0.1324, "f1": 0.1239 } }, "F5": { "complete": { "recall": 0.2881, "support": 23820 }, "obfuscated": { "recall": 0.2, "support": 15 }, "partial": { "recall": 0.0412, "support": 364 } }, "F6": { "HIGH": { "recall": 0.1718, "support": 4085 }, "LOW": { "recall": 0.1614, "support": 5088 }, "MEDIUM": { "recall": 0.3566, "support": 15026 } } }, "exact": { "tp": 5435, "fp": 38137, "fn": 18764, "precision": 0.1247, "recall": 0.2246, "f1": 0.1604, "macro_f1": 0.0529, "per_type": { "Account_Statements": { "tp": 0, "fp": 0, "fn": 75, "precision": 0, "recall": 0, "f1": 0 }, "Address_Personal": { "tp": 2, "fp": 95, "fn": 519, "precision": 0.0206, "recall": 0.0038, "f1": 0.0065 }, "Address_Work": { "tp": 0, "fp": 0, "fn": 185, "precision": 0, "recall": 0, "f1": 0 }, "Age": { "tp": 0, "fp": 0, "fn": 115, "precision": 0, "recall": 0, "f1": 0 }, "Allergy_Information": { "tp": 0, "fp": 0, "fn": 85, "precision": 0, "recall": 0, "f1": 0 }, "Building_Badge_Card_Number": { "tp": 0, "fp": 0, "fn": 43, "precision": 0, "recall": 0, "f1": 0 }, "Business_Title": { "tp": 0, "fp": 0, "fn": 537, "precision": 0, "recall": 0, "f1": 0 }, "Citizenship_Status": { "tp": 0, "fp": 0, "fn": 62, "precision": 0, "recall": 0, "f1": 0 }, "City": { "tp": 0, "fp": 0, "fn": 954, "precision": 0, "recall": 0, "f1": 0 }, "Compensation_and_Salary": { "tp": 0, "fp": 0, "fn": 219, "precision": 0, "recall": 0, "f1": 0 }, "Country_of_Residence": { "tp": 0, "fp": 0, "fn": 32, "precision": 0, "recall": 0, "f1": 0 }, "Credit_Card_Numbers": { "tp": 12, "fp": 19, "fn": 120, "precision": 0.3871, "recall": 0.0909, "f1": 0.1472 }, "Crime": { "tp": 0, "fp": 0, "fn": 114, "precision": 0, "recall": 0, "f1": 0 }, "Customer_Reference_Number": { "tp": 1097, "fp": 4008, "fn": 694, "precision": 0.2149, "recall": 0.6125, "f1": 0.3182 }, "Date_Time": { "tp": 0, "fp": 0, "fn": 1422, "precision": 0, "recall": 0, "f1": 0 }, "Date_of_Birth": { "tp": 51, "fp": 0, "fn": 535, "precision": 1, "recall": 0.087, "f1": 0.1601 }, "Disciplinary_Action": { "tp": 0, "fp": 0, "fn": 18, "precision": 0, "recall": 0, "f1": 0 }, "Driving_License_Number": { "tp": 0, "fp": 0, "fn": 41, "precision": 0, "recall": 0, "f1": 0 }, "Emergency_Contact_Details": { "tp": 0, "fp": 0, "fn": 24, "precision": 0, "recall": 0, "f1": 0 }, "Employee_ID_Number": { "tp": 0, "fp": 0, "fn": 560, "precision": 0, "recall": 0, "f1": 0 }, "First_Given_Name": { "tp": 272, "fp": 524, "fn": 2947, "precision": 0.3417, "recall": 0.0845, "f1": 0.1355 }, "Full_Name": { "tp": 2141, "fp": 3871, "fn": 2017, "precision": 0.3561, "recall": 0.5149, "f1": 0.421 }, "Gender": { "tp": 0, "fp": 0, "fn": 130, "precision": 0, "recall": 0, "f1": 0 }, "Geolocation_Data": { "tp": 0, "fp": 0, "fn": 55, "precision": 0, "recall": 0, "f1": 0 }, "Last_Family_Name": { "tp": 302, "fp": 24988, "fn": 2966, "precision": 0.0119, "recall": 0.0924, "f1": 0.0211 }, "Location": { "tp": 0, "fp": 0, "fn": 121, "precision": 0, "recall": 0, "f1": 0 }, "Marital_Status": { "tp": 0, "fp": 0, "fn": 126, "precision": 0, "recall": 0, "f1": 0 }, "Medical_Information": { "tp": 0, "fp": 0, "fn": 317, "precision": 0, "recall": 0, "f1": 0 }, "National_Identification_Number": { "tp": 12, "fp": 91, "fn": 595, "precision": 0.1165, "recall": 0.0198, "f1": 0.0338 }, "Nationality": { "tp": 0, "fp": 0, "fn": 219, "precision": 0, "recall": 0, "f1": 0 }, "Org_Name": { "tp": 101, "fp": 3430, "fn": 864, "precision": 0.0286, "recall": 0.1047, "f1": 0.0449 }, "PEP_Status": { "tp": 0, "fp": 0, "fn": 46, "precision": 0, "recall": 0, "f1": 0 }, "Passport_Number": { "tp": 0, "fp": 0, "fn": 126, "precision": 0, "recall": 0, "f1": 0 }, "Password": { "tp": 0, "fp": 0, "fn": 39, "precision": 0, "recall": 0, "f1": 0 }, "Performance_Assessment": { "tp": 0, "fp": 0, "fn": 37, "precision": 0, "recall": 0, "f1": 0 }, "Personal_Email_Address": { "tp": 0, "fp": 0, "fn": 452, "precision": 0, "recall": 0, "f1": 0 }, "Place_of_Birth": { "tp": 0, "fp": 0, "fn": 38, "precision": 0, "recall": 0, "f1": 0 }, "Political_Party": { "tp": 0, "fp": 0, "fn": 45, "precision": 0, "recall": 0, "f1": 0 }, "Preferred_Name": { "tp": 0, "fp": 0, "fn": 87, "precision": 0, "recall": 0, "f1": 0 }, "Professional_Background": { "tp": 0, "fp": 0, "fn": 33, "precision": 0, "recall": 0, "f1": 0 }, "Religion": { "tp": 0, "fp": 0, "fn": 67, "precision": 0, "recall": 0, "f1": 0 }, "Sex_Orientation": { "tp": 0, "fp": 0, "fn": 65, "precision": 0, "recall": 0, "f1": 0 }, "Sickness_Day_Records": { "tp": 0, "fp": 0, "fn": 36, "precision": 0, "recall": 0, "f1": 0 }, "Social_Media_Identifiers": { "tp": 7, "fp": 88, "fn": 174, "precision": 0.0737, "recall": 0.0387, "f1": 0.0507 }, "State": { "tp": 0, "fp": 0, "fn": 111, "precision": 0, "recall": 0, "f1": 0 }, "Static_IP_Address": { "tp": 0, "fp": 0, "fn": 103, "precision": 0, "recall": 0, "f1": 0 }, "Tax_Reference_Number": { "tp": 0, "fp": 12, "fn": 38, "precision": 0, "recall": 0, "f1": 0 }, "Telephone_Numbers_Personal": { "tp": 459, "fp": 513, "fn": 157, "precision": 0.4722, "recall": 0.7451, "f1": 0.5781 }, "Telephone_Numbers_Work": { "tp": 0, "fp": 0, "fn": 307, "precision": 0, "recall": 0, "f1": 0 }, "Trade_Union_Membership": { "tp": 0, "fp": 0, "fn": 35, "precision": 0, "recall": 0, "f1": 0 }, "Work_Email_Address": { "tp": 979, "fp": 498, "fn": 57, "precision": 0.6628, "recall": 0.945, "f1": 0.7791 } }, "per_language": { "AR": { "tp": 162, "fp": 826, "fn": 805, "precision": 0.164, "recall": 0.1675, "f1": 0.1657 }, "CS": { "tp": 265, "fp": 1812, "fn": 741, "precision": 0.1276, "recall": 0.2634, "f1": 0.1719 }, "DA": { "tp": 245, "fp": 1733, "fn": 837, "precision": 0.1239, "recall": 0.2264, "f1": 0.1601 }, "DE": { "tp": 252, "fp": 2818, "fn": 780, "precision": 0.0821, "recall": 0.2442, "f1": 0.1229 }, "EN": { "tp": 320, "fp": 1966, "fn": 775, "precision": 0.14, "recall": 0.2922, "f1": 0.1893 }, "ES": { "tp": 319, "fp": 2304, "fn": 842, "precision": 0.1216, "recall": 0.2748, "f1": 0.1686 }, "FI": { "tp": 238, "fp": 2006, "fn": 740, "precision": 0.1061, "recall": 0.2434, "f1": 0.1477 }, "FR": { "tp": 288, "fp": 652, "fn": 595, "precision": 0.3064, "recall": 0.3262, "f1": 0.316 }, "FR_CA": { "tp": 289, "fp": 594, "fn": 642, "precision": 0.3273, "recall": 0.3104, "f1": 0.3186 }, "HE": { "tp": 171, "fp": 740, "fn": 759, "precision": 0.1877, "recall": 0.1839, "f1": 0.1858 }, "HI": { "tp": 212, "fp": 1166, "fn": 701, "precision": 0.1538, "recall": 0.2322, "f1": 0.1851 }, "HU": { "tp": 231, "fp": 1450, "fn": 717, "precision": 0.1374, "recall": 0.2437, "f1": 0.1757 }, "IT": { "tp": 282, "fp": 2099, "fn": 754, "precision": 0.1184, "recall": 0.2722, "f1": 0.1651 }, "JA": { "tp": 105, "fp": 924, "fn": 797, "precision": 0.102, "recall": 0.1164, "f1": 0.1088 }, "KO": { "tp": 121, "fp": 1071, "fn": 712, "precision": 0.1015, "recall": 0.1453, "f1": 0.1195 }, "NL": { "tp": 230, "fp": 1802, "fn": 879, "precision": 0.1132, "recall": 0.2074, "f1": 0.1465 }, "NO": { "tp": 226, "fp": 1844, "fn": 669, "precision": 0.1092, "recall": 0.2525, "f1": 0.1524 }, "PT_BR": { "tp": 296, "fp": 2356, "fn": 969, "precision": 0.1116, "recall": 0.234, "f1": 0.1511 }, "PT_EU": { "tp": 206, "fp": 2135, "fn": 655, "precision": 0.088, "recall": 0.2393, "f1": 0.1287 }, "RU": { "tp": 172, "fp": 1317, "fn": 586, "precision": 0.1155, "recall": 0.2269, "f1": 0.1531 }, "SV": { "tp": 248, "fp": 1784, "fn": 772, "precision": 0.122, "recall": 0.2431, "f1": 0.1625 }, "TH": { "tp": 102, "fp": 687, "fn": 552, "precision": 0.1293, "recall": 0.156, "f1": 0.1414 }, "TR": { "tp": 279, "fp": 2323, "fn": 963, "precision": 0.1072, "recall": 0.2246, "f1": 0.1452 }, "ZH_CN": { "tp": 89, "fp": 947, "fn": 846, "precision": 0.0859, "recall": 0.0952, "f1": 0.0903 }, "ZH_TW": { "tp": 87, "fp": 781, "fn": 676, "precision": 0.1002, "recall": 0.114, "f1": 0.1067 } }, "F5": { "complete": { "recall": 0.2277, "support": 23820 }, "obfuscated": { "recall": 0.1333, "support": 15 }, "partial": { "recall": 0.022, "support": 364 } }, "F6": { "HIGH": { "recall": 0.1288, "support": 4085 }, "LOW": { "recall": 0.1071, "support": 5088 }, "MEDIUM": { "recall": 0.2904, "support": 15026 } } } } }, "file": { "route": "fichier", "fiches": 1000, "erreurs": 0, "manquantes": 0, "imbriques": 405, "directs": { "total": 17103, "touches": 16919, "caches": 15220, "touches_pct": 98.9, "caches_pct": 89, "intacts": 184 }, "niveaux": { "LOW": { "total": 5043, "touches": 4037, "caches": 3090, "touches_pct": 80.1, "caches_pct": 61.3 }, "MEDIUM": { "total": 14761, "touches": 14490, "caches": 13350, "touches_pct": 98.2, "caches_pct": 90.4 }, "HIGH": { "total": 3624, "touches": 3055, "caches": 2132, "touches_pct": 84.3, "caches_pct": 58.8 } }, "dates_de_naissance": { "total": 570, "lisibles": 357, "caches": 162, "lisibles_pct": 62.6, "caches_pct": 28.4 }, "texte_ordinaire_code_pct": { "AR": 77, "CS": 74.1, "DA": 67.3, "DE": 79.6, "EN": 24.9, "ES": 69.4, "FI": 78.3, "FR": 10.8, "FR_CA": 9.2, "HE": 66, "HI": 51.5, "HU": 74, "IT": 66.6, "JA": 74.3, "KO": 81.1, "NL": 61.7, "NO": 73, "PT_BR": 70.1, "PT_EU": 67.1, "RU": 83.6, "SV": 74.6, "TH": 79.9, "TR": 86.8, "ZH_CN": 77.5, "ZH_TW": 62.6 }, "decodage_exact": { "texte": 372, "fichier": 765, "sur": 1000 }, "officiel": { "partial": { "tp": 6794, "fp": 38135, "fn": 17405, "precision": 0.1512, "recall": 0.2808, "f1": 0.1966, "macro_f1": 0.0626, "per_type": { "Account_Statements": { "tp": 0, "fp": 0, "fn": 75, "precision": 0, "recall": 0, "f1": 0 }, "Address_Personal": { "tp": 52, "fp": 48, "fn": 469, "precision": 0.52, "recall": 0.0998, "f1": 0.1675 }, "Address_Work": { "tp": 0, "fp": 0, "fn": 185, "precision": 0, "recall": 0, "f1": 0 }, "Age": { "tp": 0, "fp": 0, "fn": 115, "precision": 0, "recall": 0, "f1": 0 }, "Allergy_Information": { "tp": 0, "fp": 0, "fn": 85, "precision": 0, "recall": 0, "f1": 0 }, "Building_Badge_Card_Number": { "tp": 0, "fp": 0, "fn": 43, "precision": 0, "recall": 0, "f1": 0 }, "Business_Title": { "tp": 0, "fp": 0, "fn": 537, "precision": 0, "recall": 0, "f1": 0 }, "Citizenship_Status": { "tp": 0, "fp": 0, "fn": 62, "precision": 0, "recall": 0, "f1": 0 }, "City": { "tp": 0, "fp": 0, "fn": 954, "precision": 0, "recall": 0, "f1": 0 }, "Compensation_and_Salary": { "tp": 0, "fp": 0, "fn": 219, "precision": 0, "recall": 0, "f1": 0 }, "Country_of_Residence": { "tp": 0, "fp": 0, "fn": 32, "precision": 0, "recall": 0, "f1": 0 }, "Credit_Card_Numbers": { "tp": 12, "fp": 20, "fn": 120, "precision": 0.375, "recall": 0.0909, "f1": 0.1463 }, "Crime": { "tp": 0, "fp": 0, "fn": 114, "precision": 0, "recall": 0, "f1": 0 }, "Customer_Reference_Number": { "tp": 1285, "fp": 3472, "fn": 506, "precision": 0.2701, "recall": 0.7175, "f1": 0.3925 }, "Date_Time": { "tp": 0, "fp": 0, "fn": 1422, "precision": 0, "recall": 0, "f1": 0 }, "Date_of_Birth": { "tp": 51, "fp": 0, "fn": 535, "precision": 1, "recall": 0.087, "f1": 0.1601 }, "Disciplinary_Action": { "tp": 0, "fp": 0, "fn": 18, "precision": 0, "recall": 0, "f1": 0 }, "Driving_License_Number": { "tp": 0, "fp": 0, "fn": 41, "precision": 0, "recall": 0, "f1": 0 }, "Emergency_Contact_Details": { "tp": 0, "fp": 0, "fn": 24, "precision": 0, "recall": 0, "f1": 0 }, "Employee_ID_Number": { "tp": 0, "fp": 0, "fn": 560, "precision": 0, "recall": 0, "f1": 0 }, "First_Given_Name": { "tp": 277, "fp": 613, "fn": 2942, "precision": 0.3112, "recall": 0.0861, "f1": 0.1348 }, "Full_Name": { "tp": 2716, "fp": 3408, "fn": 1442, "precision": 0.4435, "recall": 0.6532, "f1": 0.5283 }, "Gender": { "tp": 0, "fp": 0, "fn": 130, "precision": 0, "recall": 0, "f1": 0 }, "Geolocation_Data": { "tp": 0, "fp": 0, "fn": 55, "precision": 0, "recall": 0, "f1": 0 }, "Last_Family_Name": { "tp": 596, "fp": 25331, "fn": 2672, "precision": 0.023, "recall": 0.1824, "f1": 0.0408 }, "Location": { "tp": 0, "fp": 0, "fn": 121, "precision": 0, "recall": 0, "f1": 0 }, "Marital_Status": { "tp": 0, "fp": 0, "fn": 126, "precision": 0, "recall": 0, "f1": 0 }, "Medical_Information": { "tp": 0, "fp": 0, "fn": 317, "precision": 0, "recall": 0, "f1": 0 }, "National_Identification_Number": { "tp": 12, "fp": 87, "fn": 595, "precision": 0.1212, "recall": 0.0198, "f1": 0.034 }, "Nationality": { "tp": 0, "fp": 0, "fn": 219, "precision": 0, "recall": 0, "f1": 0 }, "Org_Name": { "tp": 290, "fp": 4100, "fn": 675, "precision": 0.0661, "recall": 0.3005, "f1": 0.1083 }, "PEP_Status": { "tp": 0, "fp": 0, "fn": 46, "precision": 0, "recall": 0, "f1": 0 }, "Passport_Number": { "tp": 0, "fp": 0, "fn": 126, "precision": 0, "recall": 0, "f1": 0 }, "Password": { "tp": 0, "fp": 0, "fn": 39, "precision": 0, "recall": 0, "f1": 0 }, "Performance_Assessment": { "tp": 0, "fp": 0, "fn": 37, "precision": 0, "recall": 0, "f1": 0 }, "Personal_Email_Address": { "tp": 0, "fp": 0, "fn": 452, "precision": 0, "recall": 0, "f1": 0 }, "Place_of_Birth": { "tp": 0, "fp": 0, "fn": 38, "precision": 0, "recall": 0, "f1": 0 }, "Political_Party": { "tp": 0, "fp": 0, "fn": 45, "precision": 0, "recall": 0, "f1": 0 }, "Preferred_Name": { "tp": 0, "fp": 0, "fn": 87, "precision": 0, "recall": 0, "f1": 0 }, "Professional_Background": { "tp": 0, "fp": 0, "fn": 33, "precision": 0, "recall": 0, "f1": 0 }, "Religion": { "tp": 0, "fp": 0, "fn": 67, "precision": 0, "recall": 0, "f1": 0 }, "Sex_Orientation": { "tp": 0, "fp": 0, "fn": 65, "precision": 0, "recall": 0, "f1": 0 }, "Sickness_Day_Records": { "tp": 0, "fp": 0, "fn": 36, "precision": 0, "recall": 0, "f1": 0 }, "Social_Media_Identifiers": { "tp": 9, "fp": 87, "fn": 172, "precision": 0.0938, "recall": 0.0497, "f1": 0.065 }, "State": { "tp": 0, "fp": 0, "fn": 111, "precision": 0, "recall": 0, "f1": 0 }, "Static_IP_Address": { "tp": 0, "fp": 0, "fn": 103, "precision": 0, "recall": 0, "f1": 0 }, "Tax_Reference_Number": { "tp": 0, "fp": 12, "fn": 38, "precision": 0, "recall": 0, "f1": 0 }, "Telephone_Numbers_Personal": { "tp": 484, "fp": 476, "fn": 132, "precision": 0.5042, "recall": 0.7857, "f1": 0.6142 }, "Telephone_Numbers_Work": { "tp": 0, "fp": 0, "fn": 307, "precision": 0, "recall": 0, "f1": 0 }, "Trade_Union_Membership": { "tp": 0, "fp": 0, "fn": 35, "precision": 0, "recall": 0, "f1": 0 }, "Work_Email_Address": { "tp": 1010, "fp": 481, "fn": 26, "precision": 0.6774, "recall": 0.9749, "f1": 0.7994 } }, "per_language": { "AR": { "tp": 183, "fp": 940, "fn": 784, "precision": 0.163, "recall": 0.1892, "f1": 0.1751 }, "CS": { "tp": 321, "fp": 1822, "fn": 685, "precision": 0.1498, "recall": 0.3191, "f1": 0.2039 }, "DA": { "tp": 319, "fp": 1736, "fn": 763, "precision": 0.1552, "recall": 0.2948, "f1": 0.2034 }, "DE": { "tp": 346, "fp": 2842, "fn": 686, "precision": 0.1085, "recall": 0.3353, "f1": 0.164 }, "EN": { "tp": 383, "fp": 1910, "fn": 712, "precision": 0.167, "recall": 0.3498, "f1": 0.2261 }, "ES": { "tp": 377, "fp": 2399, "fn": 784, "precision": 0.1358, "recall": 0.3247, "f1": 0.1915 }, "FI": { "tp": 290, "fp": 2020, "fn": 688, "precision": 0.1255, "recall": 0.2965, "f1": 0.1764 }, "FR": { "tp": 330, "fp": 603, "fn": 553, "precision": 0.3537, "recall": 0.3737, "f1": 0.3634 }, "FR_CA": { "tp": 325, "fp": 559, "fn": 606, "precision": 0.3676, "recall": 0.3491, "f1": 0.3581 }, "HE": { "tp": 190, "fp": 839, "fn": 740, "precision": 0.1846, "recall": 0.2043, "f1": 0.194 }, "HI": { "tp": 259, "fp": 1138, "fn": 654, "precision": 0.1854, "recall": 0.2837, "f1": 0.2242 }, "HU": { "tp": 281, "fp": 1427, "fn": 667, "precision": 0.1645, "recall": 0.2964, "f1": 0.2116 }, "IT": { "tp": 336, "fp": 2123, "fn": 700, "precision": 0.1366, "recall": 0.3243, "f1": 0.1923 }, "JA": { "tp": 132, "fp": 924, "fn": 770, "precision": 0.125, "recall": 0.1463, "f1": 0.1348 }, "KO": { "tp": 150, "fp": 1013, "fn": 683, "precision": 0.129, "recall": 0.1801, "f1": 0.1503 }, "NL": { "tp": 349, "fp": 1701, "fn": 760, "precision": 0.1702, "recall": 0.3147, "f1": 0.221 }, "NO": { "tp": 265, "fp": 1851, "fn": 630, "precision": 0.1252, "recall": 0.2961, "f1": 0.176 }, "PT_BR": { "tp": 426, "fp": 2272, "fn": 839, "precision": 0.1579, "recall": 0.3368, "f1": 0.215 }, "PT_EU": { "tp": 269, "fp": 2150, "fn": 592, "precision": 0.1112, "recall": 0.3124, "f1": 0.164 }, "RU": { "tp": 200, "fp": 1305, "fn": 558, "precision": 0.1329, "recall": 0.2639, "f1": 0.1768 }, "SV": { "tp": 310, "fp": 1868, "fn": 710, "precision": 0.1423, "recall": 0.3039, "f1": 0.1939 }, "TH": { "tp": 125, "fp": 739, "fn": 529, "precision": 0.1447, "recall": 0.1911, "f1": 0.1647 }, "TR": { "tp": 398, "fp": 2238, "fn": 844, "precision": 0.151, "recall": 0.3205, "f1": 0.2053 }, "ZH_CN": { "tp": 129, "fp": 944, "fn": 806, "precision": 0.1202, "recall": 0.138, "f1": 0.1285 }, "ZH_TW": { "tp": 101, "fp": 772, "fn": 662, "precision": 0.1157, "recall": 0.1324, "f1": 0.1235 } }, "F5": { "complete": { "recall": 0.2845, "support": 23820 }, "obfuscated": { "recall": 0.2, "support": 15 }, "partial": { "recall": 0.0412, "support": 364 } }, "F6": { "HIGH": { "recall": 0.1608, "support": 4085 }, "LOW": { "recall": 0.1602, "support": 5088 }, "MEDIUM": { "recall": 0.3542, "support": 15026 } } }, "exact": { "tp": 5467, "fp": 39462, "fn": 18732, "precision": 0.1217, "recall": 0.2259, "f1": 0.1582, "macro_f1": 0.0534, "per_type": { "Account_Statements": { "tp": 0, "fp": 0, "fn": 75, "precision": 0, "recall": 0, "f1": 0 }, "Address_Personal": { "tp": 2, "fp": 98, "fn": 519, "precision": 0.02, "recall": 0.0038, "f1": 0.0064 }, "Address_Work": { "tp": 0, "fp": 0, "fn": 185, "precision": 0, "recall": 0, "f1": 0 }, "Age": { "tp": 0, "fp": 0, "fn": 115, "precision": 0, "recall": 0, "f1": 0 }, "Allergy_Information": { "tp": 0, "fp": 0, "fn": 85, "precision": 0, "recall": 0, "f1": 0 }, "Building_Badge_Card_Number": { "tp": 0, "fp": 0, "fn": 43, "precision": 0, "recall": 0, "f1": 0 }, "Business_Title": { "tp": 0, "fp": 0, "fn": 537, "precision": 0, "recall": 0, "f1": 0 }, "Citizenship_Status": { "tp": 0, "fp": 0, "fn": 62, "precision": 0, "recall": 0, "f1": 0 }, "City": { "tp": 0, "fp": 0, "fn": 954, "precision": 0, "recall": 0, "f1": 0 }, "Compensation_and_Salary": { "tp": 0, "fp": 0, "fn": 219, "precision": 0, "recall": 0, "f1": 0 }, "Country_of_Residence": { "tp": 0, "fp": 0, "fn": 32, "precision": 0, "recall": 0, "f1": 0 }, "Credit_Card_Numbers": { "tp": 12, "fp": 20, "fn": 120, "precision": 0.375, "recall": 0.0909, "f1": 0.1463 }, "Crime": { "tp": 0, "fp": 0, "fn": 114, "precision": 0, "recall": 0, "f1": 0 }, "Customer_Reference_Number": { "tp": 1105, "fp": 3652, "fn": 686, "precision": 0.2323, "recall": 0.617, "f1": 0.3375 }, "Date_Time": { "tp": 0, "fp": 0, "fn": 1422, "precision": 0, "recall": 0, "f1": 0 }, "Date_of_Birth": { "tp": 51, "fp": 0, "fn": 535, "precision": 1, "recall": 0.087, "f1": 0.1601 }, "Disciplinary_Action": { "tp": 0, "fp": 0, "fn": 18, "precision": 0, "recall": 0, "f1": 0 }, "Driving_License_Number": { "tp": 0, "fp": 0, "fn": 41, "precision": 0, "recall": 0, "f1": 0 }, "Emergency_Contact_Details": { "tp": 0, "fp": 0, "fn": 24, "precision": 0, "recall": 0, "f1": 0 }, "Employee_ID_Number": { "tp": 0, "fp": 0, "fn": 560, "precision": 0, "recall": 0, "f1": 0 }, "First_Given_Name": { "tp": 271, "fp": 619, "fn": 2948, "precision": 0.3045, "recall": 0.0842, "f1": 0.1319 }, "Full_Name": { "tp": 2166, "fp": 3958, "fn": 1992, "precision": 0.3537, "recall": 0.5209, "f1": 0.4213 }, "Gender": { "tp": 0, "fp": 0, "fn": 130, "precision": 0, "recall": 0, "f1": 0 }, "Geolocation_Data": { "tp": 0, "fp": 0, "fn": 55, "precision": 0, "recall": 0, "f1": 0 }, "Last_Family_Name": { "tp": 280, "fp": 25647, "fn": 2988, "precision": 0.0108, "recall": 0.0857, "f1": 0.0192 }, "Location": { "tp": 0, "fp": 0, "fn": 121, "precision": 0, "recall": 0, "f1": 0 }, "Marital_Status": { "tp": 0, "fp": 0, "fn": 126, "precision": 0, "recall": 0, "f1": 0 }, "Medical_Information": { "tp": 0, "fp": 0, "fn": 317, "precision": 0, "recall": 0, "f1": 0 }, "National_Identification_Number": { "tp": 12, "fp": 87, "fn": 595, "precision": 0.1212, "recall": 0.0198, "f1": 0.034 }, "Nationality": { "tp": 0, "fp": 0, "fn": 219, "precision": 0, "recall": 0, "f1": 0 }, "Org_Name": { "tp": 98, "fp": 4292, "fn": 867, "precision": 0.0223, "recall": 0.1016, "f1": 0.0366 }, "PEP_Status": { "tp": 0, "fp": 0, "fn": 46, "precision": 0, "recall": 0, "f1": 0 }, "Passport_Number": { "tp": 0, "fp": 0, "fn": 126, "precision": 0, "recall": 0, "f1": 0 }, "Password": { "tp": 0, "fp": 0, "fn": 39, "precision": 0, "recall": 0, "f1": 0 }, "Performance_Assessment": { "tp": 0, "fp": 0, "fn": 37, "precision": 0, "recall": 0, "f1": 0 }, "Personal_Email_Address": { "tp": 0, "fp": 0, "fn": 452, "precision": 0, "recall": 0, "f1": 0 }, "Place_of_Birth": { "tp": 0, "fp": 0, "fn": 38, "precision": 0, "recall": 0, "f1": 0 }, "Political_Party": { "tp": 0, "fp": 0, "fn": 45, "precision": 0, "recall": 0, "f1": 0 }, "Preferred_Name": { "tp": 0, "fp": 0, "fn": 87, "precision": 0, "recall": 0, "f1": 0 }, "Professional_Background": { "tp": 0, "fp": 0, "fn": 33, "precision": 0, "recall": 0, "f1": 0 }, "Religion": { "tp": 0, "fp": 0, "fn": 67, "precision": 0, "recall": 0, "f1": 0 }, "Sex_Orientation": { "tp": 0, "fp": 0, "fn": 65, "precision": 0, "recall": 0, "f1": 0 }, "Sickness_Day_Records": { "tp": 0, "fp": 0, "fn": 36, "precision": 0, "recall": 0, "f1": 0 }, "Social_Media_Identifiers": { "tp": 7, "fp": 89, "fn": 174, "precision": 0.0729, "recall": 0.0387, "f1": 0.0505 }, "State": { "tp": 0, "fp": 0, "fn": 111, "precision": 0, "recall": 0, "f1": 0 }, "Static_IP_Address": { "tp": 0, "fp": 0, "fn": 103, "precision": 0, "recall": 0, "f1": 0 }, "Tax_Reference_Number": { "tp": 0, "fp": 12, "fn": 38, "precision": 0, "recall": 0, "f1": 0 }, "Telephone_Numbers_Personal": { "tp": 461, "fp": 499, "fn": 155, "precision": 0.4802, "recall": 0.7484, "f1": 0.585 }, "Telephone_Numbers_Work": { "tp": 0, "fp": 0, "fn": 307, "precision": 0, "recall": 0, "f1": 0 }, "Trade_Union_Membership": { "tp": 0, "fp": 0, "fn": 35, "precision": 0, "recall": 0, "f1": 0 }, "Work_Email_Address": { "tp": 1002, "fp": 489, "fn": 34, "precision": 0.672, "recall": 0.9672, "f1": 0.793 } }, "per_language": { "AR": { "tp": 154, "fp": 969, "fn": 813, "precision": 0.1371, "recall": 0.1593, "f1": 0.1474 }, "CS": { "tp": 265, "fp": 1878, "fn": 741, "precision": 0.1237, "recall": 0.2634, "f1": 0.1683 }, "DA": { "tp": 249, "fp": 1806, "fn": 833, "precision": 0.1212, "recall": 0.2301, "f1": 0.1588 }, "DE": { "tp": 255, "fp": 2933, "fn": 777, "precision": 0.08, "recall": 0.2471, "f1": 0.1209 }, "EN": { "tp": 320, "fp": 1973, "fn": 775, "precision": 0.1396, "recall": 0.2922, "f1": 0.1889 }, "ES": { "tp": 319, "fp": 2457, "fn": 842, "precision": 0.1149, "recall": 0.2748, "f1": 0.1621 }, "FI": { "tp": 244, "fp": 2066, "fn": 734, "precision": 0.1056, "recall": 0.2495, "f1": 0.1484 }, "FR": { "tp": 288, "fp": 645, "fn": 595, "precision": 0.3087, "recall": 0.3262, "f1": 0.3172 }, "FR_CA": { "tp": 288, "fp": 596, "fn": 643, "precision": 0.3258, "recall": 0.3093, "f1": 0.3174 }, "HE": { "tp": 171, "fp": 858, "fn": 759, "precision": 0.1662, "recall": 0.1839, "f1": 0.1746 }, "HI": { "tp": 215, "fp": 1182, "fn": 698, "precision": 0.1539, "recall": 0.2355, "f1": 0.1861 }, "HU": { "tp": 240, "fp": 1468, "fn": 708, "precision": 0.1405, "recall": 0.2532, "f1": 0.1807 }, "IT": { "tp": 282, "fp": 2177, "fn": 754, "precision": 0.1147, "recall": 0.2722, "f1": 0.1614 }, "JA": { "tp": 105, "fp": 951, "fn": 797, "precision": 0.0994, "recall": 0.1164, "f1": 0.1073 }, "KO": { "tp": 121, "fp": 1042, "fn": 712, "precision": 0.104, "recall": 0.1453, "f1": 0.1212 }, "NL": { "tp": 210, "fp": 1840, "fn": 899, "precision": 0.1024, "recall": 0.1894, "f1": 0.133 }, "NO": { "tp": 230, "fp": 1886, "fn": 665, "precision": 0.1087, "recall": 0.257, "f1": 0.1528 }, "PT_BR": { "tp": 302, "fp": 2396, "fn": 963, "precision": 0.1119, "recall": 0.2387, "f1": 0.1524 }, "PT_EU": { "tp": 210, "fp": 2209, "fn": 651, "precision": 0.0868, "recall": 0.2439, "f1": 0.128 }, "RU": { "tp": 179, "fp": 1326, "fn": 579, "precision": 0.1189, "recall": 0.2361, "f1": 0.1582 }, "SV": { "tp": 255, "fp": 1923, "fn": 765, "precision": 0.1171, "recall": 0.25, "f1": 0.1595 }, "TH": { "tp": 103, "fp": 761, "fn": 551, "precision": 0.1192, "recall": 0.1575, "f1": 0.1357 }, "TR": { "tp": 280, "fp": 2356, "fn": 962, "precision": 0.1062, "recall": 0.2254, "f1": 0.1444 }, "ZH_CN": { "tp": 93, "fp": 980, "fn": 842, "precision": 0.0867, "recall": 0.0995, "f1": 0.0926 }, "ZH_TW": { "tp": 89, "fp": 784, "fn": 674, "precision": 0.1019, "recall": 0.1166, "f1": 0.1088 } }, "F5": { "complete": { "recall": 0.2291, "support": 23820 }, "obfuscated": { "recall": 0.1333, "support": 15 }, "partial": { "recall": 0.022, "support": 364 } }, "F6": { "HIGH": { "recall": 0.1288, "support": 4085 }, "LOW": { "recall": 0.1071, "support": 5088 }, "MEDIUM": { "recall": 0.2926, "support": 15026 } } } } } }, "comparison": null, "published_detectors": [ { "name": "Presidio", "partial_micro_f1": 0.195, "macro_f1": 0.063, "exact_micro_f1": 0.145 }, { "name": "GLiNER-multi", "partial_micro_f1": 0.32, "macro_f1": 0.224, "exact_micro_f1": 0.293 }, { "name": "OpenAI Privacy Filter", "partial_micro_f1": 0.512, "macro_f1": 0.254, "exact_micro_f1": 0.171 }, { "name": "GPT-4.1", "partial_micro_f1": 0.597, "macro_f1": 0.565, "exact_micro_f1": 0.558 }, { "name": "Claude Sonnet 4.6", "partial_micro_f1": 0.636, "macro_f1": 0.619, "exact_micro_f1": 0.602 } ] }