{"id":"https://openalex.org/W7225013166","doi":"https://doi.org/10.5281/zenodo.23849156","title":"A Detector Score Is Not a Release Risk: What PII Detection Benchmarks Certify About Deployment, Why 'Rivals Human Annotators' and 'Fails Under Shift' Are Both Measured, and the Coverage Audit a Release Decision Needs","display_name":"A Detector Score Is Not a Release Risk: What PII Detection Benchmarks Certify About Deployment, Why 'Rivals Human Annotators' and 'Fails Under Shift' Are Both Measured, and the Coverage Audit a Release Decision Needs","publication_year":2026,"publication_date":"2026-11-01","ids":{"openalex":"https://openalex.org/W7225013166","doi":"https://doi.org/10.5281/zenodo.23849156"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23849156","doi":"https://doi.org/10.5281/zenodo.23849156","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23849156","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23849156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147720734","display_name":"Pranay M. Mahendrakar","orcid":"https://orcid.org/0009-0003-7224-029X","observed_orcids":["https://orcid.org/0009-0003-7224-029X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mahendrakar, Pranay","raw_affiliation_strings":["SONYTECH"],"raw_orcid":"https://orcid.org/0009-0003-7224-029X","affiliations":[{"raw_affiliation_string":"SONYTECH","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5147720734"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9672999978065491,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9672999978065491,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.7950000166893005},{"id":"https://openalex.org/keywords/psychiatric-records","display_name":"mental health records","score":0.4659999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083999872207642},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5426999926567078},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39259999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921000063419342},{"id":"https://openalex.org/C2776728590","wikidata":"https://www.wikidata.org/wiki/Q363948","display_name":"Contradiction","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.37860000133514404},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3718999922275543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3212999999523163},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C98347192","wikidata":"https://www.wikidata.org/wiki/Q7705804","display_name":"Test score","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23849156","doi":"https://doi.org/10.5281/zenodo.23849156","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23849156","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23849157","doi":"https://doi.org/10.5281/zenodo.23849157","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23849157","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23849156","doi":"https://doi.org/10.5281/zenodo.23849156","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23849156","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165396260","https://openalex.org/W7153825823","https://openalex.org/W7222923622","https://openalex.org/W7168322864","https://openalex.org/W7160894723","https://openalex.org/W7162294692","https://openalex.org/W7222406732","https://openalex.org/W4381432202","https://openalex.org/W6922600051","https://openalex.org/W7167018480"],"abstract_inverted_index":{"(c)":[0],"2026":[1,65,207],"Pranay":[2],"Mahendrakar.":[3],"Licensed":[4],"under":[5,77,180,187,223,233],"CC":[6],"BY":[7],"4.0.":[8],"Life":[9],"of":[10,14,116,177,211,242,256,259],"Research":[11],"Automatic":[12],"detection":[13,132],"personally":[15],"identifiable":[16],"information":[17],"(PII)":[18],"is":[19,119,262,270],"the":[20,105,117,122,128,141,146,148,153,156,163,189,198,206,212,216,260,263,271,288,299,308],"step":[21],"that":[22,69,114,137,158,273],"decides":[23],"what":[24,121,160],"text":[25,143,147],"may":[26],"leave":[27],"an":[28,279],"organisation,":[29],"and":[30,57,72,79,88,108,162,184,204,245,302],"its":[31],"published":[32,110],"record":[33],"appears":[34],"to":[35,44,112,145,215],"contradict":[36],"itself.":[37],"Clinical":[38],"de-identification":[39],"systems":[40,246],"have":[41],"been":[42],"reported":[43],"match":[45],"or":[46],"exceed":[47],"human":[48],"annotators,":[49],"with":[50,82,307],"recall":[51,84,296],"above":[52,58],"0.94":[53],"on":[54,249],"held-out":[55],"notes":[56],"0.99":[59],"for":[60,97],"one":[61,181],"rule-based":[62,71],"tool;":[63],"a":[64,89,254,265,274,291,304,311],"stress":[66,208],"test":[67,142,209],"reports":[68,92],"encoder,":[70],"language-model":[73],"detectors":[74,200],"all":[75],"degrade":[76],"noisy":[78],"informal":[80],"input,":[81],"location":[83],"falling":[85],"below":[86,95],"0.5,":[87],"unified":[90],"benchmark":[91],"span":[93],"F1":[94],"0.14":[96],"every":[98,231],"system":[99,173],"it":[100,221],"tried.":[101],"In":[102],"this":[103],"analysis":[104],"author":[106],"reviews":[107],"synthesises":[109],"results":[111],"show":[113],"most":[115],"contradiction":[118],"in":[120,127,205,290],"scores":[123,192],"index":[124],"rather":[125],"than":[126],"detectors.":[129],"A":[130,226],"PII":[131],"score":[133],"carries":[134,278],"four":[135],"indices":[136,261],"headlines":[138],"omit:":[139],"how":[140,294],"relates":[144],"detector":[149],"was":[150],"built":[151],"on,":[152],"scoring":[154],"rule,":[155],"taxonomy":[157],"defines":[159],"counts,":[161],"unit":[164],"over":[165],"which":[166,269],"misses":[167,174],"are":[168,219],"aggregated.":[169],"The":[170,285],"same":[171],"shared-task":[172],"9.1":[175],"percent":[176,186],"protected":[178],"items":[179],"official":[182],"rule":[183],"3.6":[185],"another;":[188],"lowest":[190],"unified-benchmark":[191],"come":[193],"partly":[194],"from":[195],"entity":[196],"types":[197],"evaluated":[199],"do":[201],"not":[202],"define;":[203],"several":[210],"losses":[213],"attributed":[214],"language":[217],"model":[218],"spans":[220],"covered":[222],"another":[224],"label.":[225],"residual":[227],"shift":[228],"effect":[229],"survives":[230],"index:":[232],"fixed":[234],"scoring,":[235],"cross-institution":[236],"transfer":[237],"cost":[238],"about":[239],"ten":[240],"points":[241],"strict":[243],"F1,":[244],"run":[247],"unmodified":[248],"new":[250],"psychiatric":[251],"records":[252],"scored":[253],"median":[255],"0.63.":[257],"None":[258],"quantity":[264],"release":[266,312],"decision":[267],"needs,":[268],"probability":[272],"released":[275],"document":[276,300],"still":[277],"identifying":[280],"item":[281],"someone":[282],"could":[283],"find.":[284],"paper":[286],"consolidates":[287],"evidence":[289],"table,":[292],"derives":[293],"per-item":[295],"compounds":[297],"at":[298],"level,":[301],"gives":[303],"coverage-audit":[305],"procedure":[306],"sample":[309],"sizes":[310],"claim":[313],"requires.":[314]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-11-01T00:00:00"}