{"id":"https://openalex.org/W7082992718","doi":"https://doi.org/10.1145/3749174","title":"Minimum Change\u2260 Best Cleaning: Parallel and Incremental Error Detection under Integrity Constraints","display_name":"Minimum Change\u2260 Best Cleaning: Parallel and Incremental Error Detection under Integrity Constraints","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W7082992718","doi":"https://doi.org/10.1145/3749174"},"language":"en","primary_location":{"id":"doi:10.1145/3749174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3749174","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiahui Chen","orcid":"https://orcid.org/0009-0003-9105-1961"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahui Chen","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Sun","orcid":"https://orcid.org/0009-0007-7398-2972"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Sun","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaoxu Song","orcid":"https://orcid.org/0000-0002-9503-2755"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxu Song","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haiwei Zhang","orcid":"https://orcid.org/0000-0002-5852-0426"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiwei Zhang","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaojie Yuan","orcid":"https://orcid.org/0000-0002-5876-6856"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Yuan","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73252932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.38850000500679016,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.38850000500679016,"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/T13177","display_name":"Geological and Geophysical Studies","score":0.05260000005364418,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13067","display_name":"Geological Modeling and Analysis","score":0.029400000348687172,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5558000206947327},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5464000105857849},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4796999990940094},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.44600000977516174},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4374000132083893},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.391400009393692},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.390500009059906},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.38339999318122864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466999888420105},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6096000075340271},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45179998874664307},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.391400009393692},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3749174","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3749174","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1976732638","https://openalex.org/W1992479406","https://openalex.org/W2014711341","https://openalex.org/W2044469685","https://openalex.org/W2089206172","https://openalex.org/W2108132403","https://openalex.org/W2112840274","https://openalex.org/W2162449239","https://openalex.org/W2163600218","https://openalex.org/W2164187405","https://openalex.org/W2169940602","https://openalex.org/W2170712852","https://openalex.org/W2190899134","https://openalex.org/W2544486974","https://openalex.org/W2548122763","https://openalex.org/W2591700809","https://openalex.org/W2615048832","https://openalex.org/W2618188015","https://openalex.org/W2798323405","https://openalex.org/W2799040891","https://openalex.org/W2889005129","https://openalex.org/W2921009679","https://openalex.org/W2929941791","https://openalex.org/W2948145720","https://openalex.org/W2987471611","https://openalex.org/W3030026364","https://openalex.org/W3031359560","https://openalex.org/W3164439293","https://openalex.org/W3197847098","https://openalex.org/W4235671834","https://openalex.org/W4282829255","https://openalex.org/W4312628841","https://openalex.org/W4384159544","https://openalex.org/W4396893062","https://openalex.org/W4399163976","https://openalex.org/W4401353630"],"related_works":[],"abstract_inverted_index":{"Erroneous":[0],"data":[1,15,130],"frequently":[2],"arise":[3],"in":[4,61,82,128,160,178],"practical":[5,62],"scenarios":[6],"due":[7],"to":[8,29,77,121],"a":[9],"variety":[10],"of":[11,41,173,180],"factors,":[12],"severely":[13],"degrading":[14],"quality":[16],"and":[17,36,139,148,183],"impeding":[18],"downstream":[19],"applications.":[20],"A":[21],"widely":[22],"adopted":[23],"strategy":[24],"for":[25],"error":[26,140,152,175],"detection":[27,138,153,176],"is":[28],"detect":[30],"conflicts":[31],"based":[32],"on":[33,93,167],"integrity":[34],"constraints":[35],"identify":[37,78],"the":[38,46,50,53,94,123,144,171],"minimum":[39,54,95],"number":[40],"errors,":[42],"thereby":[43],"ensuring":[44],"that":[45,85,101,155],"remaining":[47],"cells":[48,84],"satisfy":[49],"constraints.":[51],"However,":[52],"change":[55,96],"principle":[56],"may":[57],"not":[58],"be":[59,158],"applicable":[60],"scenarios,":[63],"since":[64],"errors":[65],"can":[66,156],"occur":[67],"simultaneously":[68],"or":[69],"irregularly.":[70],"Therefore,":[71],"this":[72],"study":[73],"employs":[74],"Bayesian":[75],"statistics":[76],"erroneous":[79,107],"attribute":[80,108],"values":[81,109],"conflicting":[83,110],"violate":[86],"inter-attribute":[87],"dependencies,":[88],"rather":[89],"than":[90],"simply":[91],"relying":[92],"principle.":[97],"This":[98],"approach":[99],"ensures":[100],"our":[102,174],"work":[103],"neither":[104],"misses":[105],"multiple":[106],"with":[111,143,162],"each":[112],"other":[113],"nor":[114],"mistakenly":[115],"detects":[116],"outliers":[117],"without":[118],"errors.":[119],"Furthermore,":[120],"address":[122],"efficiency":[124],"issues":[125],"commonly":[126],"encountered":[127],"constraint-based":[129],"cleaning":[131],"methods,":[132],"we":[133],"design":[134],"1)":[135],"parallel":[136,146,161],"conflict":[137],"determination":[141],"methods":[142,177],"guaranteed":[145],"scalability,":[147],"2)":[149],"efficient":[150],"incremental":[151],"strategies":[154],"also":[157],"executed":[159],"such":[163],"guarantees.":[164],"Experiments":[165],"conducted":[166],"various":[168],"datasets":[169],"demonstrate":[170],"superiority":[172],"terms":[179],"both":[181],"effectiveness":[182],"efficiency.":[184]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}