{"id":"https://openalex.org/W4390120185","doi":"https://doi.org/10.1109/tai.2023.3345805","title":"Navigating Data-Centric Artificial Intelligence With DC-Check: Advances, Challenges, and Opportunities","display_name":"Navigating Data-Centric Artificial Intelligence With DC-Check: Advances, Challenges, and Opportunities","publication_year":2023,"publication_date":"2023-12-22","ids":{"openalex":"https://openalex.org/W4390120185","doi":"https://doi.org/10.1109/tai.2023.3345805"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2023.3345805","doi":"https://doi.org/10.1109/tai.2023.3345805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3345805","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.05764","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067213867","display_name":"Nabeel Seedat","orcid":"https://orcid.org/0000-0002-2134-6639","observed_orcids":["https://orcid.org/0000-0002-2134-6639"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nabeel Seedat","raw_affiliation_strings":["University of Cambridge, Cambridge, U.K"],"raw_orcid":"https://orcid.org/0000-0002-2134-6639","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017415803","display_name":"Fergus Imrie","orcid":"https://orcid.org/0000-0002-6241-0123","observed_orcids":["https://orcid.org/0000-0002-6241-0123"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fergus Imrie","raw_affiliation_strings":["University of California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-6241-0123","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012339002","display_name":"Mihaela van der Schaar","orcid":"https://orcid.org/0000-0003-3933-6049","observed_orcids":["https://orcid.org/0000-0003-3933-6049"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mihaela van der Schaar","raw_affiliation_strings":["University of Cambridge, Cambridge, U.K","Alan Turing Institute, London, UK"],"raw_orcid":"https://orcid.org/0000-0003-3933-6049","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Alan Turing Institute, London, UK","institution_ids":["https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":2.8204,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92032347,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"5","issue":"6","first_page":"2589","last_page":"2603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.33469998836517334,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.33469998836517334,"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":0.23569999635219574,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.03970000147819519,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-centric-ai","display_name":"data-centric AI","score":0.9890000224113464},{"id":"https://openalex.org/keywords/machine-learning-pipelines","display_name":"machine learning pipelines","score":0.9079999923706055},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.7379999756813049},{"id":"https://openalex.org/keywords/data-centric-machine-learning","display_name":"data-centric machine learning","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6225787401199341},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6217111349105835},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5565283298492432},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5052040219306946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4143882393836975},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37298059463500977},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2633466124534607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08047065138816833},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tai.2023.3345805","doi":"https://doi.org/10.1109/tai.2023.3345805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3345805","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1","poland-20"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2211.05764","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.05764","pdf_url":"https://arxiv.org/pdf/2211.05764","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2211.05764","doi":"https://doi.org/10.48550/arxiv.2211.05764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.05764","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,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.05764","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.05764","pdf_url":"https://arxiv.org/pdf/2211.05764","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4286181535","display_name":"SCH: INT: Personalized Real-Time Learning of Optimal Diagnostic Tests using Multi-Modal Clinical Data","funder_award_id":"1722516","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320009","display_name":"Cystic Fibrosis Trust","ror":"https://ror.org/03xeae684"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":158,"referenced_works":["https://openalex.org/W149124899","https://openalex.org/W246024570","https://openalex.org/W1487321909","https://openalex.org/W1553101044","https://openalex.org/W1719489212","https://openalex.org/W1781481323","https://openalex.org/W1866072925","https://openalex.org/W1882958252","https://openalex.org/W2021746604","https://openalex.org/W2022477494","https://openalex.org/W2026543586","https://openalex.org/W2055400097","https://openalex.org/W2064186732","https://openalex.org/W2082087828","https://openalex.org/W2096049976","https://openalex.org/W2106505873","https://openalex.org/W2127979711","https://openalex.org/W2159291411","https://openalex.org/W2162651021","https://openalex.org/W2162888803","https://openalex.org/W2171585602","https://openalex.org/W2189149359","https://openalex.org/W2194775991","https://openalex.org/W2212660284","https://openalex.org/W2266301203","https://openalex.org/W2296719434","https://openalex.org/W2398848749","https://openalex.org/W2404161646","https://openalex.org/W2437617937","https://openalex.org/W2474194402","https://openalex.org/W2496451395","https://openalex.org/W2516809705","https://openalex.org/W2530395818","https://openalex.org/W2548122763","https://openalex.org/W2557738935","https://openalex.org/W2560321925","https://openalex.org/W2584886900","https://openalex.org/W2594183968","https://openalex.org/W2599043313","https://openalex.org/W2600383743","https://openalex.org/W2618851150","https://openalex.org/W2626778328","https://openalex.org/W2756073160","https://openalex.org/W2770173563","https://openalex.org/W2786122898","https://openalex.org/W2786814109","https://openalex.org/W2788481061","https://openalex.org/W2788633781","https://openalex.org/W2795038878","https://openalex.org/W2803106019","https://openalex.org/W2803187616","https://openalex.org/W2803403013","https://openalex.org/W2867167548","https://openalex.org/W2884061367","https://openalex.org/W2884796212","https://openalex.org/W2885593519","https://openalex.org/W2885659818","https://openalex.org/W2894566366","https://openalex.org/W2896457183","https://openalex.org/W2897042519","https://openalex.org/W2898158860","https://openalex.org/W2900572965","https://openalex.org/W2905631704","https://openalex.org/W2908109788","https://openalex.org/W2912280829","https://openalex.org/W2917760808","https://openalex.org/W2939984132","https://openalex.org/W2941345940","https://openalex.org/W2946595616","https://openalex.org/W2947014533","https://openalex.org/W2947198150","https://openalex.org/W2947280697","https://openalex.org/W2948643221","https://openalex.org/W2948689753","https://openalex.org/W2951384661","https://openalex.org/W2954395498","https://openalex.org/W2954442338","https://openalex.org/W2955443275","https://openalex.org/W2962863665","https://openalex.org/W2963341956","https://openalex.org/W2963735582","https://openalex.org/W2964155802","https://openalex.org/W2967880504","https://openalex.org/W2968009374","https://openalex.org/W2972981900","https://openalex.org/W2974817986","https://openalex.org/W2975035192","https://openalex.org/W2975257729","https://openalex.org/W2975317124","https://openalex.org/W2975583675","https://openalex.org/W2988175183","https://openalex.org/W2991497298","https://openalex.org/W2992693294","https://openalex.org/W2996061341","https://openalex.org/W2998115938","https://openalex.org/W3004146535","https://openalex.org/W3004483087","https://openalex.org/W3007508788","https://openalex.org/W3012140936","https://openalex.org/W3014596384","https://openalex.org/W3021975806","https://openalex.org/W3023521963","https://openalex.org/W3023525966","https://openalex.org/W3023533951","https://openalex.org/W3026649487","https://openalex.org/W3033733989","https://openalex.org/W3035429562","https://openalex.org/W3041133507","https://openalex.org/W3042609801","https://openalex.org/W3081464307","https://openalex.org/W3083393236","https://openalex.org/W3083961251","https://openalex.org/W3088647504","https://openalex.org/W3092527263","https://openalex.org/W3100350094","https://openalex.org/W3103694015","https://openalex.org/W3110272195","https://openalex.org/W3114973470","https://openalex.org/W3116194568","https://openalex.org/W3118813946","https://openalex.org/W3119527628","https://openalex.org/W3120894151","https://openalex.org/W3136912235","https://openalex.org/W3136933888","https://openalex.org/W3146670357","https://openalex.org/W3153872861","https://openalex.org/W3158187300","https://openalex.org/W3164582999","https://openalex.org/W3171731510","https://openalex.org/W3172701880","https://openalex.org/W3188560218","https://openalex.org/W3210418146","https://openalex.org/W3210973725","https://openalex.org/W3211244440","https://openalex.org/W3216644311","https://openalex.org/W4211049957","https://openalex.org/W4213308398","https://openalex.org/W4214942037","https://openalex.org/W4220851938","https://openalex.org/W4221145190","https://openalex.org/W4221146508","https://openalex.org/W4226307461","https://openalex.org/W4251261480","https://openalex.org/W4283070713","https://openalex.org/W4284974349","https://openalex.org/W4285796460","https://openalex.org/W4289236186","https://openalex.org/W4292121845","https://openalex.org/W4298326701","https://openalex.org/W4320340059","https://openalex.org/W4321855115","https://openalex.org/W4381611976","https://openalex.org/W6753544986","https://openalex.org/W6766132365","https://openalex.org/W6779989637","https://openalex.org/W6840059304","https://openalex.org/W6903717247","https://openalex.org/W7133222199"],"related_works":["https://openalex.org/W4406085118","https://openalex.org/W4411487348","https://openalex.org/W4365395065","https://openalex.org/W4399969224","https://openalex.org/W4392114304","https://openalex.org/W7164996674","https://openalex.org/W4312122703","https://openalex.org/W4310415176","https://openalex.org/W4380877164","https://openalex.org/W4399299414"],"abstract_inverted_index":{"Data-centric":[0],"AI":[1,26,100,124,140],"is":[2,27,85],"an":[3,73,134],"emerging":[4],"paradigm":[5],"that":[6,36,77],"emphasizes":[7],"the":[8,45,109,115,118,137,149,158],"critical":[9,68],"role":[10],"of":[11,44,54,61,111,117,136],"data":[12],"in":[13,29,105,157],"real-world":[14],"machine":[15],"learning":[16],"(ML)":[17],"systems\u2014as":[18],"a":[19,33,95,171,180],"complement":[20],"to":[21,92,98],"model":[22],"development.":[23,101],"However,":[24],"data-centric":[25,39,62,79,99,123,139],"still":[28],"its":[30,153],"infancy,":[31],"lacking":[32],"standardized":[34],"framework":[35,76],"outlines":[37],"necessary":[38],"considerations":[40,80],"at":[41,87],"various":[42],"stages":[43],"ML":[46,64,82],"pipeline:Data,":[47],"Training,":[48],"Testing,":[49],"and":[50,59,90,120,126,155,164,186],"Deployment.":[51],"This":[52],"lack":[53],"guidance":[55],"hampers":[56],"effective":[57],"communication":[58],"design":[60],"driven":[63],"systems.To":[65],"address":[66],"this":[67,146],"gap,":[69],"we":[70,107,131,169],"introduce":[71],"DC-Check,":[72,106,130],"actionable":[74],"checklist-style":[75],"encapsulates":[78],"for":[81],"systems.":[83],"DC-Check":[84,150,163,172],"aimed":[86],"both":[88],"practitioners":[89],"researchers":[91],"serve":[93,178],"as":[94,179,184],"reference":[96],"guide":[97],"Around":[102],"each":[103],"question":[104],"discuss":[108],"applicability":[110],"different":[112],"approaches,":[113],"survey":[114],"state":[116],"art,":[119],"highlight":[121],"specific":[122],"challenges":[125],"research":[127],"opportunities.While":[128],"developing":[129],"also":[132],"undertook":[133],"analysis":[135],"current":[138],"landscape.":[141],"The":[142],"insights":[143],"obtained":[144],"from":[145],"exploration":[147],"support":[148],"framework,":[151],"reinforcing":[152],"utility":[154],"relevance":[156],"rapidly":[159],"evolving":[160],"field.To":[161],"make":[162],"related":[165],"resources":[166],"easily":[167],"accessible,":[168],"provide":[170],"companion":[173],"website":[174],"(https://www.vanderschaar-lab.com/dc-check/),":[175],"which":[176],"will":[177],"living":[181],"resource,":[182],"updated":[183],"methods":[185],"tools":[187],"evolve.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2023-12-23T00:00:00"}