{"id":"https://openalex.org/W2988175183","doi":"https://doi.org/10.1613/jair.1.12125","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","display_name":"Confident Learning: Estimating Uncertainty in Dataset Labels","publication_year":2021,"publication_date":"2021-04-14","ids":{"openalex":"https://openalex.org/W2988175183","doi":"https://doi.org/10.1613/jair.1.12125","mag":"2988175183"},"language":"en","primary_location":{"id":"doi:10.1613/jair.1.12125","doi":"https://doi.org/10.1613/jair.1.12125","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.12125","pdf_url":"https://jair.org/index.php/jair/article/download/12125/26676","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jair.org/index.php/jair/article/download/12125/26676","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071352839","display_name":"Curtis G. Northcutt","orcid":"https://orcid.org/0000-0002-2423-1300","observed_orcids":["https://orcid.org/0000-0002-2423-1300"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Curtis Northcutt","raw_affiliation_strings":["Massachusetts Institute of Technology , Department of EECS , Cambridge , MA , USA","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology , Department of EECS , Cambridge , MA , USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090730336","display_name":"Lu Jiang","orcid":"https://orcid.org/0000-0003-0286-8439","observed_orcids":["https://orcid.org/0000-0003-0286-8439"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Jiang","raw_affiliation_strings":["Google Research","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103046966","display_name":"Isaac L. Chuang","orcid":"https://orcid.org/0000-0001-7296-523X","observed_orcids":["https://orcid.org/0000-0001-7296-523X"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac Chuang","raw_affiliation_strings":["Massachusetts Institute of Technology","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":34.1488,"has_fulltext":true,"cited_by_count":850,"citation_normalized_percentile":{"value":0.99856073,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"70","issue":null,"first_page":"1373","last_page":"1411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":9.999999747378752e-05,"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/T11719","display_name":"Data Quality and Management","score":0.0,"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/confident-learning","display_name":"confident learning","score":0.8799999952316284},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.7490000128746033},{"id":"https://openalex.org/keywords/label-error-detection","display_name":"label error detection","score":0.6899999976158142},{"id":"https://openalex.org/keywords/label-quality","display_name":"label quality","score":0.40700000524520874},{"id":"https://openalex.org/keywords/probabilistic-thresholds","display_name":"probabilistic thresholds","score":0.7429999709129333},{"id":"https://openalex.org/keywords/label-ranking","display_name":"label ranking","score":0.3919999897480011},{"id":"https://openalex.org/keywords/sentiment-classification","display_name":"sentiment classification","score":0.5139999985694885},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.5669999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6360061168670654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5797459483146667},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5628125071525574},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5618029832839966},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5506561994552612},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5246527194976807},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4790802597999573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4773186147212982},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4134364426136017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3945888876914978},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11985519528388977},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1613/jair.1.12125","doi":"https://doi.org/10.1613/jair.1.12125","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.12125","pdf_url":"https://jair.org/index.php/jair/article/download/12125/26676","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1911.00068","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.00068","pdf_url":"https://arxiv.org/pdf/1911.00068","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":"mag:2988175183","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1911.00068","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:dspace.mit.edu:1721.1/142946","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/142946","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"Article"},{"id":"doi:10.48550/arxiv.1911.00068","doi":"https://doi.org/10.48550/arxiv.1911.00068","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.00068","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1613/jair.1.12125","doi":"https://doi.org/10.1613/jair.1.12125","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.12125","pdf_url":"https://jair.org/index.php/jair/article/download/12125/26676","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","doaj","dongbi-b","erih-plus","jufo-3","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2988175183.pdf","grobid_xml":"https://content.openalex.org/works/W2988175183.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W167016754","https://openalex.org/W369786348","https://openalex.org/W569478347","https://openalex.org/W1488030573","https://openalex.org/W1514928307","https://openalex.org/W1580256954","https://openalex.org/W1666942233","https://openalex.org/W1861492603","https://openalex.org/W1866072925","https://openalex.org/W1877033637","https://openalex.org/W1972047492","https://openalex.org/W1980501707","https://openalex.org/W2012243161","https://openalex.org/W2048679005","https://openalex.org/W2069057270","https://openalex.org/W2107189314","https://openalex.org/W2113290770","https://openalex.org/W2117539524","https://openalex.org/W2121056381","https://openalex.org/W2123958887","https://openalex.org/W2143559571","https://openalex.org/W2146849125","https://openalex.org/W2155226385","https://openalex.org/W2156622608","https://openalex.org/W2266301203","https://openalex.org/W2337688125","https://openalex.org/W2404161646","https://openalex.org/W2468328197","https://openalex.org/W2493916176","https://openalex.org/W2531327146","https://openalex.org/W2536321907","https://openalex.org/W2590150025","https://openalex.org/W2592335154","https://openalex.org/W2598946096","https://openalex.org/W2610265803","https://openalex.org/W2611425310","https://openalex.org/W2626166918","https://openalex.org/W2626967530","https://openalex.org/W2647530754","https://openalex.org/W2743200750","https://openalex.org/W2752971446","https://openalex.org/W2762264318","https://openalex.org/W2765407302","https://openalex.org/W2770988988","https://openalex.org/W2772357980","https://openalex.org/W2785495800","https://openalex.org/W2785542264","https://openalex.org/W2803642127","https://openalex.org/W2885593519","https://openalex.org/W2897080984","https://openalex.org/W2941387380","https://openalex.org/W2943997064","https://openalex.org/W2950220847","https://openalex.org/W2952133801","https://openalex.org/W2962739340","https://openalex.org/W2962766164","https://openalex.org/W2963081269","https://openalex.org/W2963113424","https://openalex.org/W2963262394","https://openalex.org/W2963399829","https://openalex.org/W2963735582","https://openalex.org/W2963967396","https://openalex.org/W2964096266","https://openalex.org/W2964204340","https://openalex.org/W2964273174","https://openalex.org/W2964292098","https://openalex.org/W2970038028","https://openalex.org/W2970176397","https://openalex.org/W2970711760","https://openalex.org/W2979302305","https://openalex.org/W2981873476","https://openalex.org/W2983758708","https://openalex.org/W2988966271","https://openalex.org/W2990019157","https://openalex.org/W2990812465","https://openalex.org/W2996108195","https://openalex.org/W3035702670","https://openalex.org/W3087144913","https://openalex.org/W3098649723","https://openalex.org/W3118608800","https://openalex.org/W3118813946","https://openalex.org/W3146670357","https://openalex.org/W3168547821","https://openalex.org/W4287390807","https://openalex.org/W4297971002"],"related_works":["https://openalex.org/W6999417998","https://openalex.org/W3170802076","https://openalex.org/W4395677367","https://openalex.org/W4397028119","https://openalex.org/W4305028418","https://openalex.org/W4294831544","https://openalex.org/W2950198253","https://openalex.org/W4411371935","https://openalex.org/W4318185298","https://openalex.org/W3130472572"],"abstract_inverted_index":{"Learning":[0],"exists":[1],"in":[2,38,99,161,174],"the":[3,42,76,86,135,139,162,219],"context":[4],"of":[5,9,44,78],"data,":[6,47],"yet":[7],"notions":[8],"confidence":[10],"typically":[11],"focus":[12],"on":[13,29,41,75,134,171,181],"model":[14,151,203],"predictions,":[15],"not":[16,143],"label":[17,30,36,118,159],"quality.":[18],"Confident":[19],"learning":[20,130],"(CL)":[21],"is":[22,104,142],"an":[23],"alternative":[24],"approach":[25],"which":[26,103],"focuses":[27],"instead":[28],"quality":[31],"by":[32,208],"characterizing":[33],"and":[34,55,93,107,120,167,200],"identifying":[35],"errors":[37,160],"datasets,":[39],"based":[40],"principles":[43,68],"pruning":[45],"noisy":[46,90,132],"counting":[48],"with":[49,60,131],"probabilistic":[50],"thresholds":[51],"to":[52,58,83,145,156,183,212],"estimate":[53,85],"noise,":[54],"ranking":[56],"examples":[57],"train":[59],"confidence.":[61],"Whereas":[62],"numerous":[63],"studies":[64],"have":[65],"developed":[66],"these":[67],"independently,":[69],"here,":[70],"we":[71,153],"combine":[72],"them,":[73],"building":[74],"assumption":[77],"a":[79,100,146],"class-conditional":[80],"noise":[81],"process":[82],"directly":[84],"joint":[87],"distribution":[88],"between":[89],"(given)":[91],"labels":[92,133],"uncorrupted":[94],"(unknown)":[95],"labels.":[96],"This":[97],"results":[98,215],"generalized":[101],"CL":[102,115,122,140,155,180],"provably":[105],"consistent":[106],"experimentally":[108],"performant.":[109],"We":[110,177],"present":[111],"sufficient":[112],"conditions":[113],"where":[114],"exactly":[116],"finds":[117],"errors,":[119],"show":[121],"performance":[123],"exceeding":[124],"seven":[125],"recent":[126],"competitive":[127],"approaches":[128],"for":[129,206],"CIFAR":[136],"dataset.":[137],"Uniquely,":[138],"framework":[141],"coupled":[144],"specific":[147],"data":[148,173,210],"modality":[149],"or":[150],"(e.g.,":[152,188,205],"use":[154],"find":[157],"several":[158],"presumed":[163],"error-free":[164],"MNIST":[165],"dataset":[166],"improve":[168],"sentiment":[169],"classification":[170],"text":[172],"Amazon":[175],"Reviews).":[176],"also":[178],"employ":[179],"ImageNet":[182],"quantify":[184],"ontological":[185],"class":[186,198],"overlap":[187],"estimating":[189],"645":[190],"missile":[191],"images":[192],"are":[193,216],"mislabeled":[194],"as":[195],"their":[196],"parent":[197],"projectile),":[199],"moderately":[201],"increase":[202],"accuracy":[204],"ResNet)":[207],"cleaning":[209],"prior":[211],"training.":[213],"These":[214],"replicable":[217],"using":[218],"open-source":[220],"cleanlab":[221],"release.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":209},{"year":2025,"cited_by_count":166},{"year":2024,"cited_by_count":142},{"year":2023,"cited_by_count":131},{"year":2022,"cited_by_count":102},{"year":2021,"cited_by_count":73},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2019-11-22T00:00:00"}