{"id":"https://openalex.org/W7225330567","doi":"https://doi.org/10.31234/osf.io/rny7s_v1","title":"Data Diversity and Algorithmic Bias: Do Racially-Imbalanced Training Data Produce Human-Like Bias in Face Classification?","display_name":"Data Diversity and Algorithmic Bias: Do Racially-Imbalanced Training Data Produce Human-Like Bias in Face Classification?","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225330567","doi":"https://doi.org/10.31234/osf.io/rny7s_v1"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/rny7s_v1","doi":"https://doi.org/10.31234/osf.io/rny7s_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/rny7s_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31234/osf.io/rny7s_v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020657251","display_name":"Jeffrey Jordan Berg","orcid":"https://orcid.org/0000-0003-2571-1514","observed_orcids":["https://orcid.org/0000-0003-2571-1514"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Jordan Berg","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035073519","display_name":"Anke Stoll","orcid":"https://orcid.org/0009-0003-8337-2263","observed_orcids":["https://orcid.org/0009-0003-8337-2263"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anke Stoll","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159310197","display_name":"Lee Q. Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee Q. Cui","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031292184","display_name":"David Michael Amodio","orcid":"https://orcid.org/0000-0001-7746-0150","observed_orcids":["https://orcid.org/0000-0001-7746-0150"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Michael Amodio","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7746-0150","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.801800012588501,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.801800012588501,"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/T11448","display_name":"Face recognition and analysis","score":0.16439999639987946,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11094","display_name":"Face Recognition and Perception","score":0.01269999984651804,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/algorithmic-bias","display_name":"algorithmic bias","score":0.9750000238418579},{"id":"https://openalex.org/keywords/face-classification","display_name":"face classification","score":0.7059999704360962},{"id":"https://openalex.org/keywords/cross-race-effect","display_name":"cross-race effect","score":0.8460000157356262},{"id":"https://openalex.org/keywords/data-balancing","display_name":"data balancing","score":0.5220000147819519},{"id":"https://openalex.org/keywords/racial-composition","display_name":"racial composition","score":0.40400001406669617},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.4350000023841858},{"id":"https://openalex.org/keywords/human-bias","display_name":"human bias","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6389999985694885},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5856000185012817},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5410000085830688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5074999928474426},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4521999955177307},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C76509639","wikidata":"https://www.wikidata.org/wiki/Q918036","display_name":"Race (biology)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C76775654","wikidata":"https://www.wikidata.org/wiki/Q27231","display_name":"East Asia","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25850000977516174},{"id":"https://openalex.org/C56273599","wikidata":"https://www.wikidata.org/wiki/Q3122841","display_name":"White (mutation)","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31234/osf.io/rny7s_v1","doi":"https://doi.org/10.31234/osf.io/rny7s_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/rny7s_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.31234/osf.io/rny7s_v1","doi":"https://doi.org/10.31234/osf.io/rny7s_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/rny7s_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.9629999995231628}],"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/W4417337545","https://openalex.org/W7160443401","https://openalex.org/W3197722560","https://openalex.org/W7047592078","https://openalex.org/W3089144217","https://openalex.org/W3120485916","https://openalex.org/W4399623639","https://openalex.org/W4385704484","https://openalex.org/W4386246891","https://openalex.org/W7154353265"],"abstract_inverted_index":{"Can":[0],"a":[1,150,239],"lack":[2],"of":[3,12,22,154,179,235],"racial":[4,75],"diversity":[5],"in":[6,186,191,213],"training":[7,24,52,83,155,181,206],"data":[8,25,53,182,207,236],"produce":[9],"human-like":[10],"forms":[11],"AI":[13],"face":[14,27,67,71,120],"classification":[15,28,68],"bias?":[16],"We":[17,47,223],"examined":[18,49],"the":[19,44,109,199,231],"causal":[20],"effect":[21],"racially-imbalanced":[23],"on":[26,69,92],"model":[29],"disparities":[30,34,185],"and":[31,43,82,105,218,229,233],"whether":[32,50],"these":[33,55],"resemble":[35],"three":[36,58],"well-documented":[37],"human":[38,110,221],"biases\u2014the":[39],"cross-race":[40,111],"effect,":[41],"hypodescent,":[42],"gendered-race":[45,151,200],"effect.":[46,112,201],"further":[48],"balanced":[51],"mitigate":[54,242],"disparities.":[56],"In":[57,113],"experiments,":[59],"we":[60],"trained":[61,91],"deep":[62],"Vision":[63],"Transformer":[64],"models":[65,90,127,158],"for":[66,226],"16,000":[70],"images,":[72],"experimentally":[73],"manipulating":[74],"composition":[76,208],"while":[77],"holding":[78],"other":[79],"dataset":[80],"features":[81],"procedures":[84],"constant.":[85],"Study":[86,114,147],"1":[87],"showed":[88],"that":[89,205,215],"low-diversity":[93],"(majority-White)":[94],"datasets":[95],"classified":[96,159],"White":[97,132],"faces":[98,141],"more":[99,129,143,162,171],"accurately":[100,163,172],"than":[101,131,164,173],"Black,":[102],"East":[103,168,174],"Asian,":[104],"Indian":[106],"faces,":[107],"resembling":[108],"2,":[115],"using":[116],"parametrically-morphed":[117],"Black-White":[118],"biracial":[119,140,192],"images":[121],"to":[122,134,241],"estimate":[123],"race-classification":[124],"thresholds,":[125],"lower-diversity":[126],"required":[128],"Black":[130,144,160,165],"content":[133],"reach":[135],"this":[136],"threshold,":[137],"yet":[138],"represented":[139],"with":[142],"content.":[145],"Lastly,":[146],"3":[148],"revealed":[149],"effect:":[152],"regardless":[153],"set":[156],"imbalance,":[157],"men":[161],"women,":[166],"but":[167,194],"Asian":[169,175],"women":[170],"men.":[176],"The":[177],"use":[178],"racially-balanced":[180],"nearly":[183],"eliminated":[184],"monoracial":[187],"classification,":[188,193],"reduced":[189],"bias":[190],"it":[195],"did":[196],"not":[197],"alter":[198],"These":[202],"findings":[203],"show":[204],"causally":[209],"shapes":[210],"algorithmic":[211,243],"performance":[212],"ways":[214],"both":[216,230],"mimic":[217],"diverge":[219],"from":[220],"biases.":[222],"discuss":[224],"implications":[225],"AI-based":[227],"discrimination":[228],"promise":[232],"limitations":[234],"balancing":[237],"as":[238],"strategy":[240],"bias.":[244]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-06T00:00:00"}