{"id":"https://openalex.org/W4288058252","doi":"https://doi.org/10.1145/3514094.3534169","title":"Identifying Bias in Data Using Two-Distribution Hypothesis Tests","display_name":"Identifying Bias in Data Using Two-Distribution Hypothesis Tests","publication_year":2022,"publication_date":"2022-07-26","ids":{"openalex":"https://openalex.org/W4288058252","doi":"https://doi.org/10.1145/3514094.3534169"},"language":"en","primary_location":{"id":"doi:10.1145/3514094.3534169","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514094.3534169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012333376","display_name":"William Yik","orcid":"https://orcid.org/0000-0002-3918-4893"},"institutions":[{"id":"https://openalex.org/I133543626","display_name":"Harvey Mudd College","ror":"https://ror.org/025ecfn45","country_code":"US","type":"education","lineage":["https://openalex.org/I133543626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Yik","raw_affiliation_strings":["Harvey Mudd College, Claremont, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvey Mudd College, Claremont, CA, USA","institution_ids":["https://openalex.org/I133543626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031775106","display_name":"Limnanthes Serafini","orcid":null},"institutions":[{"id":"https://openalex.org/I133543626","display_name":"Harvey Mudd College","ror":"https://ror.org/025ecfn45","country_code":"US","type":"education","lineage":["https://openalex.org/I133543626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Limnanthes Serafini","raw_affiliation_strings":["Harvey Mudd College, Claremont, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvey Mudd College, Claremont, CA, USA","institution_ids":["https://openalex.org/I133543626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001132332","display_name":"Timothy Lindsey","orcid":"https://orcid.org/0000-0003-4572-9519"},"institutions":[{"id":"https://openalex.org/I152479009","display_name":"Biola University","ror":"https://ror.org/02han2n82","country_code":"US","type":"education","lineage":["https://openalex.org/I152479009"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy Lindsey","raw_affiliation_strings":["Biola University, La Mirada, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biola University, La Mirada, CA, USA","institution_ids":["https://openalex.org/I152479009"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041066830","display_name":"George D. Monta\u00f1ez","orcid":"https://orcid.org/0000-0002-1333-4611"},"institutions":[{"id":"https://openalex.org/I133543626","display_name":"Harvey Mudd College","ror":"https://ror.org/025ecfn45","country_code":"US","type":"education","lineage":["https://openalex.org/I133543626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George D. Monta\u00f1ez","raw_affiliation_strings":["Harvey Mudd College, Claremont, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvey Mudd College, Claremont, CA, USA","institution_ids":["https://openalex.org/I133543626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8501,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81069285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"831","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9614999890327454,"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/T14143","display_name":"Economic and Technological Innovation","score":0.9333999752998352,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/binomial-distribution","display_name":"Binomial distribution","score":0.6798696517944336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6432148218154907},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.6198554039001465},{"id":"https://openalex.org/keywords/binomial","display_name":"Binomial (polynomial)","score":0.5282066464424133},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.5253987908363342},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5163789987564087},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.5044366121292114},{"id":"https://openalex.org/keywords/negative-binomial-distribution","display_name":"Negative binomial distribution","score":0.4702507555484772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4573715031147003},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3480742573738098},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3392384350299835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22039324045181274}],"concepts":[{"id":"https://openalex.org/C41054675","wikidata":"https://www.wikidata.org/wiki/Q185547","display_name":"Binomial distribution","level":2,"score":0.6798696517944336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432148218154907},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6198554039001465},{"id":"https://openalex.org/C2781315470","wikidata":"https://www.wikidata.org/wiki/Q193623","display_name":"Binomial (polynomial)","level":2,"score":0.5282066464424133},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.5253987908363342},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5163789987564087},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5044366121292114},{"id":"https://openalex.org/C199335787","wikidata":"https://www.wikidata.org/wiki/Q743364","display_name":"Negative binomial distribution","level":3,"score":0.4702507555484772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4573715031147003},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3480742573738098},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3392384350299835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22039324045181274},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514094.3534169","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514094.3534169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4398744156","display_name":"REU Site: Harvey Mudd REU Site in Computer Systems","funder_award_id":"1950885","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1982376793","https://openalex.org/W2550080458","https://openalex.org/W2550530154","https://openalex.org/W2889634868","https://openalex.org/W2903891271","https://openalex.org/W2974817986","https://openalex.org/W3006719132","https://openalex.org/W3081286828","https://openalex.org/W3127529333","https://openalex.org/W3133847495","https://openalex.org/W3158735461","https://openalex.org/W3181414820","https://openalex.org/W4289548211","https://openalex.org/W4391156274"],"related_works":["https://openalex.org/W2037403216","https://openalex.org/W2021262032","https://openalex.org/W120285656","https://openalex.org/W4289107413","https://openalex.org/W2052110748","https://openalex.org/W2887966696","https://openalex.org/W4283077984","https://openalex.org/W4244236455","https://openalex.org/W62389518","https://openalex.org/W4366831151"],"abstract_inverted_index":{"As":[0],"machine":[1],"learning":[2],"models":[3],"become":[4],"more":[5],"widely":[6],"used":[7,96],"in":[8,34,77,100],"important":[9],"decision-making":[10],"processes,":[11],"the":[12,44,78,127],"need":[13,45],"for":[14,69],"identifying":[15],"and":[16,42,107],"mitigating":[17],"potential":[18,131],"sources":[19],"of":[20,90,116,134],"bias":[21,99],"has":[22],"increased":[23],"substantially.":[24],"Using":[25],"two-distribution":[26],"(specified":[27],"complexity)":[28],"hypothesis":[29,92,124],"tests,":[30,125],"we":[31],"identify":[32,98],"biases":[33,76],"training":[35],"data":[36],"with":[37,122],"respect":[38],"to":[39,46,63,97],"proposed":[40],"distributions":[41],"without":[43],"train":[47],"a":[48,65,70,87,110],"model,":[49],"distinguishing":[50],"our":[51,59,135],"methods":[52,60,136],"from":[53],"common":[54],"output-based":[55],"fairness":[56],"tests.":[57],"Furthermore,":[58],"allow":[61],"us":[62],"return":[64,109],"\"closest":[66],"plausible":[67,112],"explanation\"":[68],"given":[71],"dataset,":[72],"potentially":[73],"revealing":[74],"underlying":[75],"processes":[79],"that":[80,86],"generated":[81],"them.":[82],"We":[83],"also":[84],"show":[85],"binomial":[88,118],"variation":[89,119],"this":[91,117],"test":[93],"could":[94],"be":[95],"certain":[101,105],"directions,":[102],"or":[103],"towards":[104],"outcomes,":[106],"again":[108],"closest":[111],"explanation.":[113],"The":[114],"benefits":[115],"are":[120,137],"compared":[121],"other":[123],"including":[126],"exact":[128],"binomial.":[129],"Lastly,":[130],"industrial":[132],"applications":[133],"shown":[138],"using":[139],"two":[140],"real-world":[141],"datasets.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}