{"id":"https://openalex.org/W7155218247","doi":"https://doi.org/10.48550/arxiv.2604.19468","title":"Fairness Audits of Institutional Risk Models in Deployed ML Pipelines","display_name":"Fairness Audits of Institutional Risk Models in Deployed ML Pipelines","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155218247","doi":"https://doi.org/10.48550/arxiv.2604.19468"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19468","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.19468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018406326","display_name":"Kelly McConvey","orcid":"https://orcid.org/0000-0002-1320-7401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McConvey, Kelly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134230866","display_name":"Dipto Das","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Dipto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134343090","display_name":"Maya Ghai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghai, Maya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123544131","display_name":"Angelina Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Angelina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134356429","display_name":"Rosa Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Rosa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134274803","display_name":"Shion Guha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guha, Shion","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.40400001406669617,"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":0.40400001406669617,"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/T11122","display_name":"Online Learning and Analytics","score":0.11219999939203262,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10533","display_name":"Teaching and Learning Programming","score":0.10970000177621841,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/audit","display_name":"Audit","score":0.7157999873161316},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.4675000011920929},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3625999987125397},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.3617999851703644},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.34369999170303345}],"concepts":[{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.7157999873161316},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4341000020503998},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.43059998750686646},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C80958533","wikidata":"https://www.wikidata.org/wiki/Q1047174","display_name":"Audit trail","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3386000096797943},{"id":"https://openalex.org/C29825287","wikidata":"https://www.wikidata.org/wiki/Q1427940","display_name":"Warning system","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2986432223","wikidata":"https://www.wikidata.org/wiki/Q5449740","display_name":"Risk model","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C27504089","wikidata":"https://www.wikidata.org/wiki/Q2602080","display_name":"Audit risk","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19468","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19468","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,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.521277904510498}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fairness":[0],"audits":[1],"of":[2,38,144],"institutional":[3,49,129],"risk":[4,106,119],"models":[5],"are":[6,88,107],"critical":[7],"for":[8,91,127],"understanding":[9],"how":[10,134],"deployed":[11,40],"machine":[12],"learning":[13],"pipelines":[14],"allocate":[15],"resources.":[16],"Drawing":[17],"on":[18],"multi-year":[19],"collaboration":[20],"with":[21,103],"Centennial":[22],"College,":[23],"where":[24],"our":[25],"prior":[26],"ethnographic":[27],"work":[28,122],"introduced":[29],"the":[30,65,142],"ASP-HEI":[31],"Cycle,":[32],"we":[33],"present":[34],"a":[35,39,124,157],"replica-based":[36],"audit":[37,79],"Early":[41],"Warning":[42],"System":[43],"(EWS),":[44],"replicating":[45],"its":[46],"model":[47,70],"using":[48,74],"training":[50],"data":[51],"and":[52,61,72,85,100,132,137,164],"design":[53],"specifications.":[54],"We":[55],"evaluate":[56],"disparities":[57,112,135],"by":[58,113],"gender,":[59],"age,":[60],"residency":[62],"status":[63],"across":[64,139],"full":[66],"pipeline":[67],"(training":[68],"data,":[69,163],"predictions,":[71],"post-processing)":[73],"standard":[75],"fairness":[76],"metrics.":[77],"Our":[78],"reveals":[80],"systematic":[81],"misallocation:":[82],"younger,":[83],"male,":[84],"international":[86],"students":[87,102],"disproportionately":[89],"flagged":[90],"support,":[92],"even":[93],"when":[94],"many":[95],"ultimately":[96],"succeed,":[97],"while":[98],"older":[99],"female":[101],"comparable":[104],"dropout":[105],"under-identified.":[108],"Post-processing":[109],"amplifies":[110],"these":[111],"collapsing":[114],"heterogeneous":[115],"probabilities":[116],"into":[117],"percentile-based":[118],"tiers.":[120],"This":[121],"provides":[123],"replicable":[125],"methodology":[126],"auditing":[128],"ML":[130],"systems":[131],"shows":[133],"emerge":[136],"compound":[138],"stages,":[140],"highlighting":[141],"importance":[143],"evaluating":[145],"construct":[146],"validity":[147],"alongside":[148],"statistical":[149],"fairness.":[150],"It":[151],"contributes":[152],"one":[153],"empirical":[154],"thread":[155],"to":[156],"broader":[158],"program":[159],"investigating":[160],"algorithms,":[161],"student":[162],"power":[165],"in":[166],"higher":[167],"education.":[168]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-23T00:00:00"}