{"id":"https://openalex.org/W7214354570","doi":"https://doi.org/10.48550/arxiv.2609.29580","title":"When Identical Rows Disagree: From Benchmark Identifiability to Replication-Robust Anomaly Detection","display_name":"When Identical Rows Disagree: From Benchmark Identifiability to Replication-Robust Anomaly Detection","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7214354570","doi":"https://doi.org/10.48550/arxiv.2609.29580"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.29580","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29580","pdf_url":"https://arxiv.org/pdf/2609.29580","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.29580","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152793173","display_name":"Jie Deng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Deng, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5152793173"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9970999956130981,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9970999956130981,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.000699999975040555,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.000699999975040555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"anomaly detection","score":0.7549999952316284},{"id":"https://openalex.org/keywords/scouts","display_name":"Scouts","score":0.6850000023841858},{"id":"https://openalex.org/keywords/false-positive-rate-control","display_name":"false positive rate control","score":0.6470000147819519},{"id":"https://openalex.org/keywords/isolation-forest","display_name":"Isolation Forest","score":0.6010000109672546},{"id":"https://openalex.org/keywords/rate-heterogeneity","display_name":"rate heterogeneity","score":0.48899999260902405}],"concepts":[{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.6656000018119812},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.6626999974250793},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5720000267028809},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5117999911308289},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48910000920295715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.4796999990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4004000127315521},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3659000098705292},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C77246614","wikidata":"https://www.wikidata.org/wiki/Q1409400","display_name":"Gramian matrix","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2526000142097473},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.29580","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29580","pdf_url":"https://arxiv.org/pdf/2609.29580","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.29580","doi":"https://doi.org/10.48550/arxiv.2609.29580","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.29580","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.29580","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29580","pdf_url":"https://arxiv.org/pdf/2609.29580","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214354570.pdf","grobid_xml":"https://content.openalex.org/works/W7214354570.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7218337183","https://openalex.org/W7156372801","https://openalex.org/W7166713226","https://openalex.org/W7161233674","https://openalex.org/W7214597251","https://openalex.org/W3092385390","https://openalex.org/W7220746434","https://openalex.org/W7204215674","https://openalex.org/W7212303648","https://openalex.org/W3153418084"],"abstract_inverted_index":{"A":[0],"released":[1],"table":[2],"is":[3,47,138,155],"often":[4],"treated":[5,205],"as":[6,206],"an":[7,41],"i.i.d.":[8],"sample,":[9],"although":[10],"its":[11],"repeated":[12,18],"rows":[13,39],"may":[14],"encode":[15],"business":[16],"frequency,":[17],"entities,":[19],"joins,":[20],"resampling,":[21],"or":[22,209],"extraction":[23],"errors.":[24],"We":[25,107],"show":[26,186],"that":[27,118,187],"this":[28],"ambiguity":[29],"creates":[30],"a":[31,55,77,82,114],"hidden":[32],"measurement":[33],"layer":[34],"with":[35],"three":[36],"consequences:":[37],"feature-identical":[38,71],"impose":[40],"attained":[42],"evaluation":[43],"ceiling,":[44],"row-weighted":[45],"AUROC":[46,94,163],"sensitive":[48],"to":[49,81,90,141,157],"replication,":[50],"and":[51,76,150,164,175],"row-trained":[52],"detectors":[53],"learn":[54],"multiplicity-size-biased":[56],"law.":[57],"An":[58],"exact-row":[59],"audit":[60],"of":[61],"all":[62],"690":[63],"OddBench":[64,148],"datasets":[65,101,149],"finds":[66],"train-test":[67],"overlap":[68],"in":[69,74,85,161],"355,":[70],"label":[72],"conflict":[73],"147,":[75],"test":[78],"anomaly":[79,116],"identical":[80],"training":[83],"normal":[84],"137.":[86],"Switching":[87],"from":[88,123],"row":[89,144],"support":[91,121,136],"weighting":[92],"changes":[93],"by":[95],"at":[96],"least":[97],"0.05":[98],"on":[99],"50-61":[100],"across":[102],"four":[103,176],"classical":[104],"detector":[105,117],"geometries.":[106],"introduce":[108],"SCOUT":[109,154],"(Support-Count":[110],"Orthogonalized":[111],"Unsupervised":[112],"Testing),":[113],"factorized":[115],"separates":[119],"replication-invariant":[120,166],"evidence":[122],"exposure-aware":[124],"count":[125,189],"evidence.":[126],"Factorwise":[127],"split-conformal":[128],"calibration":[129],"yields":[130],"marginal":[131],"false-positive-rate":[132],"control,":[133],"while":[134],"the":[135],"channel":[137],"exactly":[139,179],"invariant":[140],"arbitrary":[142],"positive":[143],"replication.":[145,183],"On":[146],"686":[147],"five":[151],"seeds,":[152],"support-only":[153],"non-inferior":[156],"row-wise":[158],"Isolation":[159],"Forest":[160],"raw":[162],"improves":[165],"AUROC.":[167],"External":[168],"normal-support":[169],"evaluations":[170],"track":[171],"nominal":[172],"false-positive":[173],"levels,":[174],"backbones":[177],"remain":[178],"unchanged":[180],"under":[181,194],"controlled":[182],"Semi-synthetic":[184],"interventions":[185],"conditional":[188],"modeling":[190],"helps":[191],"materially":[192],"only":[193],"strong":[195],"rate":[196],"heterogeneity.":[197],"These":[198],"results":[199],"specify":[200],"when":[201],"multiplicity":[202],"should":[203],"be":[204],"signal,":[207],"nuisance,":[208],"uninterpretable":[210],"without":[211],"additional":[212],"information.":[213]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-26T00:00:00"}