{"id":"https://openalex.org/W4412877122","doi":"https://doi.org/10.1145/3711896.3737422","title":"DCA-Bench: A Benchmark for Dataset Curation Agents","display_name":"DCA-Bench: A Benchmark for Dataset Curation Agents","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877122","doi":"https://doi.org/10.1145/3711896.3737422"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737422","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737422","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737422","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101298780","display_name":"Benhao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benhao Huang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0003-5449-2813","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111227792","display_name":"Yingzhuo Yu","orcid":"https://orcid.org/0000-0003-3782-6888"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingzhuo Yu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-3782-6888","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112333775","display_name":"Jin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin Huang","raw_affiliation_strings":["University of Michigan - Ann Arbor, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0009-0009-1780-2513","affiliations":[{"raw_affiliation_string":"University of Michigan - Ann Arbor, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102769254","display_name":"Xingjian Zhang","orcid":"https://orcid.org/0009-0001-0716-3449"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xingjian Zhang","raw_affiliation_strings":["University of Michigan - Ann Arbor, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0009-0001-0716-3449","affiliations":[{"raw_affiliation_string":"University of Michigan - Ann Arbor, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089063294","display_name":"Jiaqi Ma","orcid":"https://orcid.org/0000-0001-8292-5901"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi W. Ma","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-8292-5901","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4641,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91951006,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5482","last_page":"5492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9944999814033508,"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/T11937","display_name":"Research Data Management Practices","score":0.9847000241279602,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8047215938568115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7097622752189636},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5574773550033569},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45445939898490906},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3365331292152405},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07115653157234192},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06811368465423584}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8047215938568115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7097622752189636},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5574773550033569},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45445939898490906},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3365331292152405},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07115653157234192},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06811368465423584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737422","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737422","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737422","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737422","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877122.pdf","grobid_xml":"https://content.openalex.org/works/W4412877122.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2132862423","https://openalex.org/W2302501749","https://openalex.org/W3081464307","https://openalex.org/W3119246366","https://openalex.org/W4285272262","https://openalex.org/W4303614602","https://openalex.org/W4320814215","https://openalex.org/W4378978494","https://openalex.org/W4385571232","https://openalex.org/W4389519254","https://openalex.org/W4392414327","https://openalex.org/W4401042136","https://openalex.org/W6600459194","https://openalex.org/W6602855854","https://openalex.org/W6893628702"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W4306317641","https://openalex.org/W1488337274","https://openalex.org/W4287611188","https://openalex.org/W2216178707"],"abstract_inverted_index":{"The":[0,221],"quality":[1,28,192],"of":[2,14,22,85,96,189,201],"datasets":[3],"plays":[4],"an":[5,155],"increasingly":[6],"crucial":[7],"role":[8],"in":[9,43,116,194],"the":[10,20,82,94,117,190,195,199],"research":[11],"and":[12,38,53,64,76,153,204,219,223],"development":[13],"modern":[15],"artificial":[16],"intelligence":[17],"(AI).":[18],"Despite":[19],"proliferation":[21],"open":[23],"dataset":[24,67,98,151,212],"platforms":[25,152],"nowadays,":[26],"data":[27,191,222],"issues,":[29],"such":[30],"as":[31],"incomplete":[32],"documentation,":[33],"inaccurate":[34],"labels,":[35],"ethical":[36],"concerns,":[37],"outdated":[39],"information,":[40],"remain":[41],"common":[42],"widely":[44],"used":[45],"datasets.":[46],"Furthermore,":[47],"these":[48],"issues":[49,99,115,193],"are":[50],"often":[51],"subtle":[52],"difficult":[54],"to":[55,78,92,113,132,137,210],"be":[56],"detected":[57],"by":[58,66],"rule-based":[59],"scripts,":[60],"therefore":[61],"requiring":[62],"identification":[63],"verification":[65],"users":[68],"or":[69],"maintainers-a":[70],"process":[71],"that":[72,206],"is":[73,109,225],"both":[74],"time-consuming":[75],"prone":[77],"human":[79,176],"mistakes.":[80],"With":[81],"surging":[83],"ability":[84,136],"large":[86],"language":[87],"models":[88],"(LLM),":[89],"it's":[90],"promising":[91],"streamline":[93],"discovery":[95],"hidden":[97],"with":[100,168,175],"LLM":[101,111,134,208],"agents.":[102],"To":[103],"achieve":[104],"this,":[105],"one":[106],"significant":[107],"challenge":[108],"enabling":[110],"agents":[112,209],"detect":[114],"wild":[118],"rather":[119],"than":[120],"simply":[121],"fixing":[122],"known":[123],"ones.":[124],"In":[125],"this":[126,139,202],"work,":[127],"we":[128],"establish":[129],"a":[130],"benchmark":[131],"measure":[133],"agent's":[135],"tackle":[138],"challenge.":[140],"We":[141],"carefully":[142],"curate":[143],"221":[144],"real-world":[145,211],"test":[146],"cases":[147],"from":[148],"eight":[149],"popular":[150],"propose":[154],"automatic":[156],"evaluation":[157],"framework":[158,163],"using":[159],"GPT-4o.":[160],"Our":[161],"proposed":[162,196],"shows":[164],"strong":[165],"empirical":[166],"alignment":[167],"expert":[169],"evaluations,":[170],"validated":[171],"through":[172],"extensive":[173],"comparisons":[174],"annotations.":[177],"Without":[178],"any":[179],"hints,":[180],"most":[181],"competitive":[182],"Curator":[183],"agent":[184],"can":[185],"only":[186],"reveal":[187],"~30%":[188],"dataset,":[197],"highlighting":[198],"complexity":[200],"task":[203],"indicating":[205],"applying":[207],"curation":[213],"still":[214],"requires":[215],"further":[216],"in-depth":[217],"exploration":[218],"innovation.":[220],"code":[224],"available":[226],"at":[227],"https://github.com/TRAIS-Lab/dca-bench.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}