{"id":"https://openalex.org/W2889005129","doi":"https://doi.org/10.14778/3236187.3236193","title":"Explaining repaired data with CFDs","display_name":"Explaining repaired data with CFDs","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2889005129","doi":"https://doi.org/10.14778/3236187.3236193","mag":"2889005129"},"language":"en","primary_location":{"id":"doi:10.14778/3236187.3236193","doi":"https://doi.org/10.14778/3236187.3236193","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3236187.3236193","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","norway-2","poland-20","russia-white-list-1","vabb-shw"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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":"https://openalex.org/A5062717336","display_name":"Joeri Rammelaere","orcid":"https://orcid.org/0000-0003-1256-165X","observed_orcids":["https://orcid.org/0000-0003-1256-165X"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Joeri Rammelaere","raw_affiliation_strings":["University of Antwerp, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087587379","display_name":"Floris Geerts","orcid":"https://orcid.org/0000-0002-8967-2473","observed_orcids":["https://orcid.org/0000-0002-8967-2473"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Floris Geerts","raw_affiliation_strings":["University of Antwerp, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Antwerp, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149213910"],"apc_list":null,"apc_paid":null,"fwci":3.0692,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92639545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"11","issue":"11","first_page":"1387","last_page":"1399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9907000064849854,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.006099999882280827,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.0003000000142492354,"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-cleaning","display_name":"data cleaning","score":0.8949999809265137},{"id":"https://openalex.org/keywords/conditional-functional-dependencies","display_name":"conditional functional dependencies","score":0.9449999928474426},{"id":"https://openalex.org/keywords/user-feedback","display_name":"user feedback","score":0.5690000057220459},{"id":"https://openalex.org/keywords/constraint-discovery","display_name":"constraint discovery","score":0.7940000295639038},{"id":"https://openalex.org/keywords/data-repair","display_name":"data repair","score":0.4970000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751080989837646},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6996785998344421},{"id":"https://openalex.org/C58625266","wikidata":"https://www.wikidata.org/wiki/Q1256418","display_name":"Lode","level":2,"score":0.6691733598709106},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5270749926567078},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5239639282226562},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4604215621948242},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4408458471298218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3434869050979614},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3314470052719116},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1706167757511139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.109058678150177},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3236187.3236193","doi":"https://doi.org/10.14778/3236187.3236193","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3236187.3236193","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","norway-2","poland-20","russia-white-list-1","vabb-shw"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1516723845","https://openalex.org/W1967167578","https://openalex.org/W1976732638","https://openalex.org/W1994962776","https://openalex.org/W1997952460","https://openalex.org/W2029052075","https://openalex.org/W2029570660","https://openalex.org/W2039548475","https://openalex.org/W2041442195","https://openalex.org/W2046298800","https://openalex.org/W2047745978","https://openalex.org/W2051200809","https://openalex.org/W2056748234","https://openalex.org/W2063103859","https://openalex.org/W2078132546","https://openalex.org/W2099637074","https://openalex.org/W2113607096","https://openalex.org/W2133409729","https://openalex.org/W2142472956","https://openalex.org/W2145346822","https://openalex.org/W2149664453","https://openalex.org/W2166549982","https://openalex.org/W2167333415","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2188696002","https://openalex.org/W2190899134","https://openalex.org/W2238711864","https://openalex.org/W2266772167","https://openalex.org/W2298871042","https://openalex.org/W2401565948","https://openalex.org/W2481573984","https://openalex.org/W2591114563","https://openalex.org/W2613390631","https://openalex.org/W2614592379","https://openalex.org/W2618188015","https://openalex.org/W3106124465","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W4312157405","https://openalex.org/W2913572352","https://openalex.org/W7100520108","https://openalex.org/W2021255304","https://openalex.org/W2778368504","https://openalex.org/W4306816470","https://openalex.org/W7098255803","https://openalex.org/W2185579824","https://openalex.org/W7098052692","https://openalex.org/W2113607096"],"abstract_inverted_index":{"Many":[0],"popular":[1],"data":[2,15,133],"cleaning":[3,141],"approaches":[4],"are":[5,8,21,25],"rule-based:":[6],"Constraints":[7],"formulated":[9],"in":[10,184],"a":[11,64,78,82,126,159,177],"logical":[12],"framework,":[13],"and":[14,88,146,179],"is":[16,37,46,167,180],"considered":[17],"dirty":[18,86],"if":[19],"constraints":[20,24,45],"violated.":[22],"These":[23],"often":[26],"discovered":[27,44],"from":[28],"data,":[29],"but":[30],"to":[31,182],"ascertain":[32],"their":[33],"validity,":[34],"user":[35,56,69,79],"verification":[36],"necessary.":[38],"Since":[39],"the":[40,59,73,76,91,109,122,151,185],"full":[41],"set":[42,84],"of":[43,75,85,103,162],"typically":[47,155],"too":[48],"large":[49],"for":[50,125],"manual":[51],"inspection,":[52],"recent":[53],"research":[54],"integrates":[55],"feedback":[57],"into":[58],"discovery":[60],"process.":[61],"We":[62,100,112],"propose":[63],"different":[65],"approach":[66],"that":[67,150,174],"employs":[68],"interaction":[70],"only":[71],"at":[72],"start":[74],"algorithm:":[77],"manually":[80],"cleans":[81],"small":[83],"tuples,":[87],"we":[89],"infer":[90],"constraint":[92,110],"underlying":[93],"those":[94],"repairs,":[95],"called":[96],"an":[97,117],"explanation":[98,124,153],".":[99],"make":[101],"use":[102],"conditional":[104],"functional":[105],"dependencies":[106],"(CFDs)":[107],"as":[108],"formalism.":[111],"introduce":[113],"XP":[114,165],"lode":[115,166],",":[116],"on-demand":[118],"algorithm":[119],"which":[120],"discovers":[121],"best":[123,152],"given":[127],"repair.":[128],"Guided":[129],"by":[130],"this":[131],"explanation,":[132],"can":[134,154],"then":[135],"be":[136,156],"cleaned":[137],"using":[138,158],"state-of-the-art":[139],"CFD-based":[140],"algorithms.":[142],"Experiments":[143],"on":[144,176],"synthetic":[145],"real-world":[147],"datasets":[148],"show":[149],"inferred":[157],"limited":[160],"number":[161],"modifications.":[163,186],"Moreover,":[164],"substantially":[168],"faster":[169],"than":[170],"discovering":[171],"all":[172],"CFDs":[173],"hold":[175],"dataset,":[178],"robust":[181],"noise":[183]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-09-07T00:00:00"}