{"id":"https://openalex.org/W4283156082","doi":"https://doi.org/10.1145/3531146.3533086","title":"A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication","display_name":"A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication","publication_year":2022,"publication_date":"2022-06-20","ids":{"openalex":"https://openalex.org/W4283156082","doi":"https://doi.org/10.1145/3531146.3533086"},"language":"en","primary_location":{"id":"doi:10.1145/3531146.3533086","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531146.3533086","pdf_url":null,"source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"type":"article","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/A5091714241","display_name":"Alexandra Sasha Luccioni","orcid":"https://orcid.org/0000-0001-6238-7050"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alexandra Sasha Luccioni","raw_affiliation_strings":["Hugging Face, Canada"],"affiliations":[{"raw_affiliation_string":"Hugging Face, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037656113","display_name":"Frances Corry","orcid":"https://orcid.org/0000-0002-0503-2410"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frances Corry","raw_affiliation_strings":["University of Southern California, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049788579","display_name":"Hamsini Sridharan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamsini Sridharan","raw_affiliation_strings":["University of Southern California, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060322803","display_name":"Mike Ananny","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Ananny","raw_affiliation_strings":["University of Southern California, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025721704","display_name":"Jason Schultz","orcid":null},"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":"Jason Schultz","raw_affiliation_strings":["New York University, USA"],"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033954307","display_name":"Kate Crawford","orcid":"https://orcid.org/0000-0001-9972-7194"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kate Crawford","raw_affiliation_strings":["University of Southern California, USA and Microsoft Research, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, USA and Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091714241"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5792,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85092509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9976000189781189,"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":0.9976000189781189,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9968000054359436,"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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8091827630996704},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.7905262112617493},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.7579800486564636},{"id":"https://openalex.org/keywords/stewardship","display_name":"Stewardship (theology)","score":0.6798657178878784},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5132415294647217},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.5023844242095947},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.48782089352607727},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43631380796432495},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3447098731994629},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3218318521976471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091827630996704},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7905262112617493},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.7579800486564636},{"id":"https://openalex.org/C2777950569","wikidata":"https://www.wikidata.org/wiki/Q17021836","display_name":"Stewardship (theology)","level":3,"score":0.6798657178878784},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5132415294647217},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.5023844242095947},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48782089352607727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43631380796432495},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3447098731994629},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3218318521976471},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3531146.3533086","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531146.3533086","pdf_url":null,"source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Responsible consumption and production","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1488996941","https://openalex.org/W2022493637","https://openalex.org/W2099757732","https://openalex.org/W2102381086","https://openalex.org/W2102709386","https://openalex.org/W2108598243","https://openalex.org/W2353949686","https://openalex.org/W2564513428","https://openalex.org/W2580365077","https://openalex.org/W2747597535","https://openalex.org/W2802138801","https://openalex.org/W2808589232","https://openalex.org/W2897042519","https://openalex.org/W2907258563","https://openalex.org/W2912218663","https://openalex.org/W2919193235","https://openalex.org/W2963780471","https://openalex.org/W2989947149","https://openalex.org/W2998508940","https://openalex.org/W3004542466","https://openalex.org/W3014972121","https://openalex.org/W3027379683","https://openalex.org/W3035296331","https://openalex.org/W3035442500","https://openalex.org/W3039108075","https://openalex.org/W3084611909","https://openalex.org/W3089066314","https://openalex.org/W3096214574","https://openalex.org/W3100191342","https://openalex.org/W3100279624","https://openalex.org/W3125419471","https://openalex.org/W3127162919","https://openalex.org/W3154155772","https://openalex.org/W3174269049","https://openalex.org/W3174372618","https://openalex.org/W3180969989","https://openalex.org/W3189849087","https://openalex.org/W3204130547","https://openalex.org/W3206774279","https://openalex.org/W3207830467","https://openalex.org/W3212464620","https://openalex.org/W3213241618","https://openalex.org/W4200297327","https://openalex.org/W4220752914","https://openalex.org/W4226151601","https://openalex.org/W4288083803"],"related_works":["https://openalex.org/W1858249912","https://openalex.org/W2114034199","https://openalex.org/W2317428717","https://openalex.org/W2734259032","https://openalex.org/W4385261515","https://openalex.org/W3094038556","https://openalex.org/W4296345146","https://openalex.org/W2014772881","https://openalex.org/W4254228154","https://openalex.org/W3049477255"],"abstract_inverted_index":{"Datasets":[0],"are":[1,43],"central":[2],"to":[3,17,76],"training":[4],"machine":[5],"learning":[6],"(ML)":[7],"models.":[8],"The":[9],"ML":[10,127],"community":[11],"has":[12,37],"recently":[13],"made":[14],"significant":[15],"improvements":[16],"data":[18],"stewardship":[19,152],"and":[20,41,82,89,116,123,146,151,159],"documentation":[21],"practices":[22,148],"across":[23],"the":[24,30,53,62,84,126],"model":[25],"development":[26],"life":[27,55],"cycle.":[28,56],"However,":[29],"act":[31],"of":[32,52,64,72,106,109,149],"deprecating,":[33],"or":[34,144],"deleting,":[35],"datasets":[36,73],"been":[38,80],"largely":[39],"overlooked,":[40],"there":[42],"currently":[44],"no":[45],"standardized":[46],"approaches":[47],"for":[48,138],"structuring":[49],"this":[50,58],"stage":[51],"dataset":[54,65,142],"In":[57],"paper,":[59],"we":[60,130],"study":[61],"practice":[63],"deprecation":[66],"in":[67],"ML,":[68],"identify":[69],"several":[70],"cases":[71],"that":[74,103,119,153],"continued":[75],"circulate":[77],"despite":[78],"having":[79],"deprecated,":[81],"describe":[83],"different":[85],"technical,":[86],"legal,":[87],"ethical,":[88],"organizational":[90],"issues":[91],"raised":[92],"by":[93,125],"such":[94],"continuations.":[95],"We":[96],"then":[97],"propose":[98,131],"a":[99,133],"Dataset":[100],"Deprecation":[101],"Framework":[102],"includes":[104],"considerations":[105],"risk,":[107],"mitigation":[108],"impact,":[110],"appeal":[111],"mechanisms,":[112],"timeline,":[113],"post-deprecation":[114],"protocols,":[115],"publication":[117,160],"checks":[118],"can":[120,154],"be":[121,155],"adapted":[122],"implemented":[124],"community.":[128],"Finally,":[129],"creating":[132],"centralized,":[134],"sustainable":[135],"repository":[136],"system":[137],"archiving":[139],"datasets,":[140],"tracking":[141],"modifications":[143],"deprecations,":[145],"facilitating":[147],"care":[150],"integrated":[156],"into":[157],"research":[158],"processes.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
