{"id":"https://openalex.org/W4396786982","doi":"https://doi.org/10.1145/3630106.3658955","title":"Machine learning data practices through a data curation lens: An evaluation framework","display_name":"Machine learning data practices through a data curation lens: An evaluation framework","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4396786982","doi":"https://doi.org/10.1145/3630106.3658955"},"language":"en","primary_location":{"id":"doi:10.1145/3630106.3658955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658955","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071400231","display_name":"Eshta Bhardwaj","orcid":"https://orcid.org/0000-0001-8523-5201"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Eshta Bhardwaj","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043066037","display_name":"Harshit Gujral","orcid":"https://orcid.org/0000-0001-5152-1971"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Harshit Gujral","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103018919","display_name":"Siyi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Siyi Wu","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065203672","display_name":"Ciara Zogheib","orcid":"https://orcid.org/0000-0002-0620-3007"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ciara Zogheib","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061026145","display_name":"Tegan Maharaj","orcid":"https://orcid.org/0000-0002-7370-0978"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tegan Maharaj","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101397764","display_name":"Christoph Becker","orcid":"https://orcid.org/0000-0002-8364-0593"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christoph Becker","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5071400231"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":2.7046,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91031265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1055","last_page":"1067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9937000274658203,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9937000274658203,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9908999800682068,"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/T11937","display_name":"Research Data Management Practices","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/data-curation","display_name":"Data curation","score":0.9127379059791565},{"id":"https://openalex.org/keywords/rubric","display_name":"Rubric","score":0.7585166692733765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7384099960327148},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5903339385986328},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.4928913116455078},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.4684607684612274},{"id":"https://openalex.org/keywords/best-practice","display_name":"Best practice","score":0.42821264266967773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.411529541015625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.390962153673172},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3360697031021118}],"concepts":[{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.9127379059791565},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.7585166692733765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384099960327148},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5903339385986328},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.4928913116455078},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4684607684612274},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.42821264266967773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.411529541015625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.390962153673172},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3360697031021118},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3630106.3658955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658955","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.02703","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.02703","pdf_url":"https://arxiv.org/pdf/2405.02703","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3630106.3658955","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3658955","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3658955","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1597412403","display_name":null,"funder_award_id":"RGPIN-","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3216283581","display_name":null,"funder_award_id":"RGPIN-201","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G4884591305","display_name":null,"funder_award_id":"RGPIN-2016-06640","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G6221715925","display_name":null,"funder_award_id":"RGPIN","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G7977925233","display_name":null,"funder_award_id":"RGPIN-2016-06","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396786982.pdf"},"referenced_works_count":88,"referenced_works":["https://openalex.org/W213371629","https://openalex.org/W919098568","https://openalex.org/W935072310","https://openalex.org/W1567491469","https://openalex.org/W1968183008","https://openalex.org/W1997772859","https://openalex.org/W2015997502","https://openalex.org/W2063085086","https://openalex.org/W2067724039","https://openalex.org/W2106238660","https://openalex.org/W2110783479","https://openalex.org/W2120096569","https://openalex.org/W2125590838","https://openalex.org/W2157004265","https://openalex.org/W2159818719","https://openalex.org/W2302501749","https://openalex.org/W2327837586","https://openalex.org/W2793785670","https://openalex.org/W2798615872","https://openalex.org/W2889059162","https://openalex.org/W2897042519","https://openalex.org/W2897154134","https://openalex.org/W2910401125","https://openalex.org/W2910548926","https://openalex.org/W2911227954","https://openalex.org/W2930813675","https://openalex.org/W2934302500","https://openalex.org/W2940891023","https://openalex.org/W2941766203","https://openalex.org/W2949697405","https://openalex.org/W2953532875","https://openalex.org/W2963349562","https://openalex.org/W2981575922","https://openalex.org/W3014972121","https://openalex.org/W3016224608","https://openalex.org/W3024722698","https://openalex.org/W3100279624","https://openalex.org/W3101243562","https://openalex.org/W3102195403","https://openalex.org/W3104128335","https://openalex.org/W3118813946","https://openalex.org/W3126911807","https://openalex.org/W3133702157","https://openalex.org/W3133764719","https://openalex.org/W3135371071","https://openalex.org/W3157353160","https://openalex.org/W3163469193","https://openalex.org/W3165300194","https://openalex.org/W3166873126","https://openalex.org/W3180721273","https://openalex.org/W3181414820","https://openalex.org/W3189849087","https://openalex.org/W3194157648","https://openalex.org/W3204381272","https://openalex.org/W3204800293","https://openalex.org/W3206271843","https://openalex.org/W3207830467","https://openalex.org/W3208177503","https://openalex.org/W3212368439","https://openalex.org/W3212464620","https://openalex.org/W3213556453","https://openalex.org/W4205570006","https://openalex.org/W4210916416","https://openalex.org/W4220923293","https://openalex.org/W4224990248","https://openalex.org/W4225109361","https://openalex.org/W4229441612","https://openalex.org/W4231012597","https://openalex.org/W4282813546","https://openalex.org/W4288083797","https://openalex.org/W4288083800","https://openalex.org/W4288083802","https://openalex.org/W4288096724","https://openalex.org/W4288359825","https://openalex.org/W4292121845","https://openalex.org/W4293240666","https://openalex.org/W4293802067","https://openalex.org/W4306698380","https://openalex.org/W4308784155","https://openalex.org/W4309618982","https://openalex.org/W4312481174","https://openalex.org/W4313450386","https://openalex.org/W4322717806","https://openalex.org/W4378044967","https://openalex.org/W4383218913","https://openalex.org/W4386545054","https://openalex.org/W4388492808","https://openalex.org/W4388654737"],"related_works":["https://openalex.org/W1987813225","https://openalex.org/W4390610055","https://openalex.org/W4379053243","https://openalex.org/W3021020626","https://openalex.org/W2955201676","https://openalex.org/W2153005530","https://openalex.org/W3199392376","https://openalex.org/W4321385307","https://openalex.org/W2330342969","https://openalex.org/W2050399338"],"abstract_inverted_index":{"Studies":[0],"of":[1,29,65,104,115,163,183,197,212],"dataset":[2,60,214],"development":[3,18,61],"in":[4,57,72,127,141,174,186,193,208],"machine":[5,48,58,73,88,123,142,243],"learning":[6,59,74,89,124,244],"call":[7],"for":[8,86,107,122,231],"greater":[9,41],"attention":[10],"to":[11,119,150,202,222],"the":[12,27,63,113,161,195,204,210],"data":[13,36,55,66,70,76,92,116,125,132,153,198,236,245],"practices":[14,32,56,71],"that":[15,26,139,170,233],"make":[16],"model":[17,147],"possible":[19],"and":[20,31,35,45,95,129,206,226,239],"shape":[21],"its":[22],"outcomes.":[23],"Many":[24],"argue":[25],"adoption":[28],"theory":[30],"from":[33],"archives":[34],"curation":[37,77,93,117,133,154,199,237],"fields":[38,176],"can":[39,241],"support":[40],"fairness,":[42],"accountability,":[43],"transparency,":[44],"more":[46],"ethical":[47],"learning.":[49],"In":[50],"response,":[51],"this":[52],"paper":[53],"examines":[54],"through":[62,97],"lens":[64],"curation.":[67],"We":[68,137,219],"evaluate":[69],"as":[75,167],"practices.":[78,246],"To":[79],"do":[80],"so,":[81],"we":[82,111],"develop":[83,227],"a":[84,98,101,180],"framework":[85,230],"evaluating":[87,168],"datasets":[90],"using":[91],"concepts":[94,188,238],"principles":[96,118],"rubric.":[99],"Through":[100],"mixed-methods":[102],"analysis":[103],"evaluation":[105,232],"results":[106],"25":[108],"ML":[109],"datasets,":[110],"study":[112],"feasibility":[114],"be":[120],"adopted":[121],"work":[126],"practice":[128],"explore":[130],"how":[131,235],"is":[134],"currently":[135],"performed.":[136],"find":[138],"researchers":[140],"learning,":[143],"which":[144],"often":[145],"emphasizes":[146],"development,":[148],"struggle":[149],"apply":[151,203],"standard":[152],"principles.":[155],"Our":[156],"findings":[157],"illustrate":[158],"difficulties":[159],"at":[160],"intersection":[162],"these":[164,224],"fields,":[165],"such":[166],"dimensions":[169],"have":[171],"shared":[172],"terms":[173],"both":[175],"but":[177],"non-shared":[178],"meanings,":[179],"high":[181],"degree":[182],"interpretative":[184],"flexibility":[185],"adapting":[187],"without":[189],"prescriptive":[190],"restrictions,":[191],"obstacles":[192],"limiting":[194],"depth":[196],"expertise":[200],"needed":[201],"rubric,":[205],"challenges":[207,225],"scoping":[209],"extent":[211],"documentation":[213],"creators":[215],"are":[216],"responsible":[217],"for.":[218],"propose":[220],"ways":[221],"address":[223],"an":[228],"overall":[229],"outlines":[234],"methods":[240],"inform":[242]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}