{"id":"https://openalex.org/W7166504177","doi":"https://doi.org/10.1145/3805689.3812313","title":"\u201cDetective Work We Shouldn't Have to Do\u201d: Practitioner Challenges in Regulatory-Aligned Data Quality in Machine Learning Systems","display_name":"\u201cDetective Work We Shouldn't Have to Do\u201d: Practitioner Challenges in Regulatory-Aligned Data Quality in Machine Learning Systems","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166504177","doi":"https://doi.org/10.1145/3805689.3812313"},"language":null,"primary_location":{"id":"doi:10.1145/3805689.3812313","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812313","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805689.3812313","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125657936","display_name":"Y Y Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yichun Wang","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0009-0005-9218-3290","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012472912","display_name":"Kristina Irion","orcid":"https://orcid.org/0000-0003-4151-1520"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kristina Irion","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4151-1520","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034924491","display_name":"Paul Groth","orcid":"https://orcid.org/0000-0003-0183-6910"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paul Groth","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0183-6910","affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008534205","display_name":"Hazar Harmouch","orcid":"https://orcid.org/0000-0001-9967-5347"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hazar Harmouch","raw_affiliation_strings":["Informatics Institute, University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-9967-5347","affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83578644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3217","last_page":"3241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.31929999589920044,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.31929999589920044,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.13459999859333038,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.0737999975681305,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.5317999720573425},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4555000066757202},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4142000079154968},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.31690001487731934},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2840000092983246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5590000152587891},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48899999260902405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4142000079154968},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C203481301","wikidata":"https://www.wikidata.org/wiki/Q76221","display_name":"Data system","level":2,"score":0.24869999289512634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805689.3812313","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812313","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805689.3812313","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812313","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1567491469","https://openalex.org/W2162651021","https://openalex.org/W2167541073","https://openalex.org/W2407300725","https://openalex.org/W2489600561","https://openalex.org/W2766279925","https://openalex.org/W2766945679","https://openalex.org/W2768181417","https://openalex.org/W2769968138","https://openalex.org/W2782864149","https://openalex.org/W2786242872","https://openalex.org/W2796141164","https://openalex.org/W2888134164","https://openalex.org/W2889249015","https://openalex.org/W2893405045","https://openalex.org/W2897154134","https://openalex.org/W2910548926","https://openalex.org/W2936503027","https://openalex.org/W2948897128","https://openalex.org/W3001807593","https://openalex.org/W3014972121","https://openalex.org/W3037921969","https://openalex.org/W3133893548","https://openalex.org/W3135371071","https://openalex.org/W3156669901","https://openalex.org/W3158479996","https://openalex.org/W3180969989","https://openalex.org/W3185723659","https://openalex.org/W3212368439","https://openalex.org/W4280609065","https://openalex.org/W4281723109","https://openalex.org/W4308784155","https://openalex.org/W4308914439","https://openalex.org/W4310261382","https://openalex.org/W4319299406","https://openalex.org/W4366407820","https://openalex.org/W4380361082","https://openalex.org/W4384025135","https://openalex.org/W4387176601","https://openalex.org/W4387294395","https://openalex.org/W4399362525","https://openalex.org/W4399364234","https://openalex.org/W4402650617","https://openalex.org/W4403908451","https://openalex.org/W4406085118","https://openalex.org/W4409883896","https://openalex.org/W4411550051","https://openalex.org/W4411550541"],"related_works":[],"abstract_inverted_index":{"Ensuring":[0],"data":[1,38,73,91,117,156],"quality":[2,39,137],"in":[3,46,79],"machine":[4],"learning":[5],"(ML)":[6],"systems":[7,78],"has":[8],"become":[9],"increasingly":[10],"complex":[11],"as":[12,23,102],"regulatory":[13],"requirements":[14,40],"expand.":[15],"In":[16],"the":[17,24,31,93,98],"European":[18],"Union":[19],"(EU),":[20],"frameworks":[21],"such":[22],"General":[25],"Data":[26],"Protection":[27],"Regulation":[28],"(GDPR)":[29],"and":[30,60,97,112,128,131,150],"Artificial":[32],"Intelligence":[33],"Act":[34],"(AI":[35],"Act)":[36],"articulate":[37],"that":[41],"closely":[42],"parallel":[43],"technical":[44,127],"concerns":[45],"ML":[47,77],"practice,":[48],"while":[49],"also":[50,140],"extending":[51],"to":[52,56],"legal":[53,110,129],"obligations":[54],"related":[55],"accountability,":[57],"risk":[58],"management,":[59],"human":[61],"rights":[62],"protection.":[63],"This":[64],"paper":[65],"presents":[66],"a":[67,132,152],"qualitative":[68],"interview":[69],"study":[70],"with":[71],"EU-based":[72],"practitioners":[74,88],"working":[75],"on":[76],"regulated":[80],"contexts.":[81],"Through":[82],"semi-structured":[83],"interviews,":[84],"we":[85],"investigate":[86],"how":[87],"interpret":[89],"regulatory-aligned":[90,155],"quality,":[92],"challenges":[94],"they":[95,100],"encounter,":[96],"support":[99],"identify":[101,141],"necessary.":[103],"Our":[104],"findings":[105],"reveal":[106],"persistent":[107],"gaps":[108],"between":[109,126],"principles":[111],"engineering":[113],"workflows,":[114],"fragmentation":[115],"across":[116],"pipelines,":[118],"limitations":[119],"of":[120,154],"existing":[121],"tools,":[122],"unclear":[123],"responsibility":[124],"boundaries":[125],"teams,":[130],"tendency":[133],"towards":[134],"reactive,":[135],"audit-driven":[136],"practices.":[138],"We":[139],"practitioners'":[142],"needs":[143],"for":[144],"compliance-aware":[145],"tooling,":[146],"clearer":[147],"governance":[148],"structures,":[149],"promoting":[151],"culture":[153],"quality.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-30T00:00:00"}