{"id":"https://openalex.org/W4367190906","doi":"https://doi.org/10.1145/3593078.3593930","title":"AutoCure: Automated Tabular Data Curation Technique for ML Pipelines","display_name":"AutoCure: Automated Tabular Data Curation Technique for ML Pipelines","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4367190906","doi":"https://doi.org/10.1145/3593078.3593930"},"language":"en","primary_location":{"id":"doi:10.1145/3593078.3593930","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3593078.3593930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.13636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101773285","display_name":"Mohamed Abdelaal","orcid":"https://orcid.org/0009-0006-4561-4761"},"institutions":[{"id":"https://openalex.org/I4210087817","display_name":"Software (Germany)","ror":"https://ror.org/004g36n56","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210087817"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mohamed Abdelaal","raw_affiliation_strings":["Software AG, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0009-0006-4561-4761","affiliations":[{"raw_affiliation_string":"Software AG, Darmstadt, Germany","institution_ids":["https://openalex.org/I4210087817"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053464267","display_name":"Rashmi Koparde","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rashmi Koparde","raw_affiliation_strings":["Otto von Guericke University Magdebur, Magdeburg, Germany"],"raw_orcid":"https://orcid.org/0009-0005-8509-7247","affiliations":[{"raw_affiliation_string":"Otto von Guericke University Magdebur, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110960188","display_name":"Harald Schoening","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087817","display_name":"Software (Germany)","ror":"https://ror.org/004g36n56","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210087817"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Harald Schoening","raw_affiliation_strings":["Software AG, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4480-8269","affiliations":[{"raw_affiliation_string":"Software AG, Darmstadt, Germany","institution_ids":["https://openalex.org/I4210087817"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11719","display_name":"Data Quality and Management","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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":0.9887999892234802,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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-curation","display_name":"Data curation","score":0.8286807537078857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7648941874504089},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6662791967391968},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4516063630580902},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.42926838994026184},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.417233943939209},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40865445137023926},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10719171166419983}],"concepts":[{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.8286807537078857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648941874504089},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6662791967391968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4516063630580902},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.42926838994026184},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.417233943939209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40865445137023926},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10719171166419983},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"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":2,"locations":[{"id":"doi:10.1145/3593078.3593930","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3593078.3593930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.13636","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13636","pdf_url":"https://arxiv.org/pdf/2304.13636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.13636","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13636","pdf_url":"https://arxiv.org/pdf/2304.13636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1287636682","display_name":null,"funder_award_id":"01IS21021A (ITEA project number 20219)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G7826384177","display_name":null,"funder_award_id":"02L19C155","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320313144","display_name":"ITEA","ror":null},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367190906.pdf","grobid_xml":"https://content.openalex.org/works/W4367190906.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1559060276","https://openalex.org/W1959608418","https://openalex.org/W1992479406","https://openalex.org/W2046298800","https://openalex.org/W2064186732","https://openalex.org/W2157564217","https://openalex.org/W2190899134","https://openalex.org/W2232417456","https://openalex.org/W2298871042","https://openalex.org/W2544486974","https://openalex.org/W2548122763","https://openalex.org/W2767280887","https://openalex.org/W2808833850","https://openalex.org/W2901320906","https://openalex.org/W2929941791","https://openalex.org/W2948145720","https://openalex.org/W2949244208","https://openalex.org/W2949676527","https://openalex.org/W2962897394","https://openalex.org/W2978725006","https://openalex.org/W2987471611","https://openalex.org/W2997756720","https://openalex.org/W3021459486","https://openalex.org/W3082197983","https://openalex.org/W3096831136","https://openalex.org/W3105977086","https://openalex.org/W3120740533","https://openalex.org/W3122755912","https://openalex.org/W3135991645","https://openalex.org/W3136021864","https://openalex.org/W3205420294","https://openalex.org/W4213178287","https://openalex.org/W4244467125","https://openalex.org/W4247007654","https://openalex.org/W4320342846","https://openalex.org/W4320342899","https://openalex.org/W4381747115"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W1787170397","https://openalex.org/W4292347844"],"abstract_inverted_index":{"Machine":[0],"learning":[1,167],"algorithms":[2],"have":[3],"become":[4],"increasingly":[5],"prevalent":[6],"in":[7,26],"multiple":[8],"domains,":[9,19],"such":[10,18],"as":[11],"autonomous":[12],"driving,":[13],"healthcare,":[14],"and":[15,33,46,58,92,110,142,161],"finance.":[16],"In":[17,97],"data":[20,44,60,72,83,94,136,159],"preparation":[21,160],"remains":[22],"a":[23,56,93,120,126],"significant":[24,31],"challenge":[25],"developing":[27],"accurate":[28],"models,":[29],"requiring":[30],"expertise":[32],"time":[34],"investment":[35],"to":[36,112,157],"explore":[37],"the":[38,65,78,81,114,163],"huge":[39],"search":[40],"space":[41],"of":[42,67,80,116,122,129,134,165],"well-suited":[43],"curation":[45,61,73,137],"transformation":[47],"tools.":[48],"To":[49],"address":[50],"this":[51],"challenge,":[52],"we":[53,124],"present":[54],"AutoCure,":[55],"novel":[57],"configuration-free":[59],"pipeline":[62],"that":[63,151],"improves":[64],"quality":[66],"tabular":[68],"data.":[69],"Unlike":[70],"traditional":[71,135],"methods,":[74],"AutoCure":[75,99,130,152],"synthetically":[76],"enhances":[77],"density":[79],"clean":[82],"fraction":[84],"through":[85],"an":[86,154],"adaptive":[87],"ensemble-based":[88],"error":[89],"detection":[90],"method":[91],"augmentation":[95],"module.":[96],"practice,":[98],"can":[100],"be":[101],"integrated":[102],"with":[103],"open":[104],"source":[105],"tools,":[106,138],"e.g.,":[107],"Auto-sklearn,":[108],"H2O,":[109],"TPOT,":[111],"promote":[113],"democratization":[115],"machine":[117,166],"learning.":[118],"As":[119],"proof":[121],"concept,":[123],"provide":[125],"comparative":[127],"evaluation":[128,149],"against":[131],"28":[132],"combinations":[133],"demonstrating":[139],"superior":[140],"performance":[141],"predictive":[143],"accuracy":[144,164],"without":[145],"user":[146],"intervention.":[147],"Our":[148],"shows":[150],"is":[153],"effective":[155],"approach":[156],"automating":[158],"improving":[162],"models.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}