{"id":"https://openalex.org/W7130543688","doi":"https://doi.org/10.1145/3772318.3791344","title":"From Reflection to Repair: A Scoping Review of Dataset Documentation Tools","display_name":"From Reflection to Repair: A Scoping Review of Dataset Documentation Tools","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7130543688","doi":"https://doi.org/10.1145/3772318.3791344"},"language":null,"primary_location":{"id":"doi:10.1145/3772318.3791344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791344","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772318.3791344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058319194","display_name":"Pedro Reynolds-Cu\u00e9llar","orcid":"https://orcid.org/0000-0001-5690-1850"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Reynolds-Cu\u00e9llar","raw_affiliation_strings":["Robotics, Ethics and Society, Robotics and AI Institute, Cambridge, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0001-5690-1850","affiliations":[{"raw_affiliation_string":"Robotics, Ethics and Society, Robotics and AI Institute, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019858112","display_name":"Marisol Wong-Villacr\u00e9s","orcid":null},"institutions":[{"id":"https://openalex.org/I2135383","display_name":"Escuela Superior Politecnica del Litoral","ror":"https://ror.org/04qenc566","country_code":"EC","type":"education","lineage":["https://openalex.org/I2135383"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Marisol Wong-Villacres","raw_affiliation_strings":["Facultad de Ingenier\u00eda en Electricidad y Computaci\u00f3n, Escuela Superior Polit\u00e9cnica del Litoral, Guayaquil, Ecuador"],"raw_orcid":"https://orcid.org/0000-0002-8071-6716","affiliations":[{"raw_affiliation_string":"Facultad de Ingenier\u00eda en Electricidad y Computaci\u00f3n, Escuela Superior Polit\u00e9cnica del Litoral, Guayaquil, Ecuador","institution_ids":["https://openalex.org/I2135383"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067725152","display_name":"Adriana Alvarado Garcia","orcid":"https://orcid.org/0000-0002-4230-3777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adriana Alvarado Garcia","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-4230-3777","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018740466","display_name":"Heila Precel","orcid":"https://orcid.org/0009-0005-2580-7040"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heila Precel","raw_affiliation_strings":["Faculty of Computing &amp; Data Sciences, Boston University, Boston, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0009-0005-2580-7040","affiliations":[{"raw_affiliation_string":"Faculty of Computing &amp; Data Sciences, Boston University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I33434090"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13349633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"25"},"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":0.6074000000953674,"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":0.6074000000953674,"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/T10260","display_name":"Software Engineering Research","score":0.031099999323487282,"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"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.025599999353289604,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.9653000235557556},{"id":"https://openalex.org/keywords/conceptualization","display_name":"Conceptualization","score":0.734499990940094},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.4194999933242798},{"id":"https://openalex.org/keywords/internal-documentation","display_name":"Internal documentation","score":0.3790999948978424},{"id":"https://openalex.org/keywords/technical-documentation","display_name":"Technical documentation","score":0.3280999958515167},{"id":"https://openalex.org/keywords/user-analysis","display_name":"User analysis","score":0.3093999922275543}],"concepts":[{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.9653000235557556},{"id":"https://openalex.org/C90734943","wikidata":"https://www.wikidata.org/wiki/Q17008777","display_name":"Conceptualization","level":2,"score":0.734499990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4361000061035156},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.4300999939441681},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3905999958515167},{"id":"https://openalex.org/C140396857","wikidata":"https://www.wikidata.org/wiki/Q16934771","display_name":"Internal documentation","level":5,"score":0.3790999948978424},{"id":"https://openalex.org/C25688753","wikidata":"https://www.wikidata.org/wiki/Q1413406","display_name":"Technical documentation","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C93430992","wikidata":"https://www.wikidata.org/wiki/Q7901834","display_name":"User analysis","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C81587897","wikidata":"https://www.wikidata.org/wiki/Q181702","display_name":"Software documentation","level":5,"score":0.2621999979019165},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2615000009536743},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3772318.3791344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791344","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.15968","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.15968","pdf_url":"https://arxiv.org/pdf/2602.15968","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3772318.3791344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791344","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dataset":[0],"documentation":[1,19,32,53,61,66,88,145],"is":[2,26],"widely":[3],"recognized":[4],"as":[5,112],"essential":[6],"for":[7],"the":[8,29,36,57,137],"responsible":[9],"development":[10],"of":[11,23,50,98],"automated":[12],"systems.":[13],"Despite":[14],"growing":[15],"efforts":[16],"to":[17,55,73,109,142],"support":[18],"through":[20],"different":[21],"kinds":[22],"artifacts,":[24],"little":[25],"known":[27],"about":[28],"motivations":[30,58],"shaping":[31],"tool":[33,126],"design":[34,127],"or":[35],"factors":[37],"hindering":[38],"their":[39],"adoption.":[40],"We":[41],"present":[42],"a":[43,107,121],"systematic":[44],"review":[45],"supported":[46],"by":[47],"mixed-methods":[48],"analysis":[49,81],"59":[51],"dataset":[52,87],"publications":[54],"examine":[56],"behind":[59],"building":[60],"tools,":[62],"how":[63,69],"authors":[64],"conceptualize":[65],"practices,":[67],"and":[68,77,94,106,134],"these":[70,117],"tools":[71],"connect":[72],"existing":[74],"systems,":[75],"regulations,":[76],"cultural":[78],"norms.":[79],"Our":[80],"shows":[82],"four":[83],"persistent":[84],"patterns":[85],"in":[86,123],"conceptualization":[89],"that":[90],"potentially":[91],"impede":[92],"adoption":[93],"standardization:":[95],"unclear":[96],"operationalizations":[97],"documentation\u2019s":[99],"value,":[100],"decontextualized":[101],"designs,":[102],"unaddressed":[103],"labor":[104],"demands,":[105],"tendency":[108],"treat":[110],"integration":[111],"future":[113],"work.":[114],"Building":[115],"on":[116],"findings,":[118],"we":[119],"propose":[120],"shift":[122],"Responsible":[124],"AI":[125],"toward":[128],"institutional":[129],"rather":[130],"than":[131],"individual":[132],"solutions,":[133],"outline":[135],"actions":[136],"HCI":[138],"community":[139],"can":[140],"take":[141],"enable":[143],"sustainable":[144],"practices.":[146]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-20T00:00:00"}
