{"id":"https://openalex.org/W1573646728","doi":"https://doi.org/10.1109/icde.2015.7113269","title":"Proof positive and negative in data cleaning","display_name":"Proof positive and negative in data cleaning","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1573646728","doi":"https://doi.org/10.1109/icde.2015.7113269","mag":"1573646728"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2015.7113269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2015.7113269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 31st International Conference on Data Engineering","raw_type":"proceedings-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":"https://openalex.org/A5071206013","display_name":"Matteo Interlandi","orcid":"https://orcid.org/0000-0002-5756-8321"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Matteo Interlandi","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar","Qatar Computing Research Institute [Doha, Qatar]"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]},{"raw_affiliation_string":"Qatar Computing Research Institute [Doha, Qatar]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071206013"],"corresponding_institution_ids":["https://openalex.org/I1301390666"],"apc_list":null,"apc_paid":null,"fwci":8.8135,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9762705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.998199999332428,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9749000072479248,"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/computer-science","display_name":"Computer science","score":0.7207571268081665},{"id":"https://openalex.org/keywords/proof-of-concept","display_name":"Proof of concept","score":0.7183437943458557},{"id":"https://openalex.org/keywords/data-integrity","display_name":"Data integrity","score":0.6383774280548096},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5868916511535645},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5834170579910278},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5171922445297241},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5083004832267761},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41604089736938477},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3499378561973572},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32657569646835327},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20018166303634644},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17143583297729492},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16332736611366272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1624891459941864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1095641553401947},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.09625974297523499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207571268081665},{"id":"https://openalex.org/C124978682","wikidata":"https://www.wikidata.org/wiki/Q1201019","display_name":"Proof of concept","level":2,"score":0.7183437943458557},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.6383774280548096},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5868916511535645},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5834170579910278},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5171922445297241},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5083004832267761},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41604089736938477},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3499378561973572},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32657569646835327},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20018166303634644},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17143583297729492},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16332736611366272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1624891459941864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1095641553401947},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.09625974297523499},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2015.7113269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2015.7113269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 31st International Conference on Data Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W4175336","https://openalex.org/W1545761598","https://openalex.org/W1547556487","https://openalex.org/W1875064445","https://openalex.org/W1967167578","https://openalex.org/W1980706971","https://openalex.org/W1990028388","https://openalex.org/W1994529543","https://openalex.org/W1997952460","https://openalex.org/W2008271340","https://openalex.org/W2037594241","https://openalex.org/W2044022210","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2047745978","https://openalex.org/W2059009730","https://openalex.org/W2063103859","https://openalex.org/W2077518845","https://openalex.org/W2078132546","https://openalex.org/W2081186682","https://openalex.org/W2089206172","https://openalex.org/W2112840274","https://openalex.org/W2113415503","https://openalex.org/W2113607096","https://openalex.org/W2131060875","https://openalex.org/W2137775416","https://openalex.org/W2147805208","https://openalex.org/W2161163216","https://openalex.org/W2163600218","https://openalex.org/W2164187405","https://openalex.org/W2167333415","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2178708778","https://openalex.org/W3000214033","https://openalex.org/W6600161640","https://openalex.org/W6639152687","https://openalex.org/W6645410415","https://openalex.org/W6670179770","https://openalex.org/W6679898556","https://openalex.org/W6680599078","https://openalex.org/W6683456455"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W2138823233","https://openalex.org/W2023236823","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W2101053337","https://openalex.org/W1840581861"],"abstract_inverted_index":{"One":[0],"notoriously":[1],"hard":[2],"data":[3,35,42,61,91,107,158,172,181],"cleaning":[4,43,157],"problem":[5],"is,":[6],"given":[7],"a":[8,58,66,117],"database,":[9],"how":[10,138],"to":[11,33,139],"precisely":[12],"capture":[13,34],"which":[14,73],"value":[15,74],"is":[16,69,75,82,185],"correct":[17],"(i.e.,":[18,23],"proof":[19,24,76,102,129,134,174],"positive)":[20],"or":[21,78],"wrong":[22],"negative).":[25],"Although":[26],"integrity":[27,45,85],"constraints":[28,46,86],"have":[29],"been":[30,49],"widely":[31],"studied":[32],"errors":[36],"as":[37],"violations,":[38],"the":[39],"accuracy":[40],"of":[41,60,72],"using":[44,159],"has":[47],"long":[48],"controversial.":[50],"Overall":[51],"they":[52],"deem":[53],"one":[54],"fundamental":[55,145],"problem:":[56],"Given":[57,116],"set":[59],"values":[62],"that":[63,84,165],"together":[64],"forms":[65],"violation,":[67],"there":[68],"no":[70],"evidence":[71],"positive":[77,103,175],"negative.":[79],"Hence,":[80],"it":[81],"known":[83],"themselves":[87],"cannot":[88],"guide":[89],"dependable":[90],"cleaning.":[92],"In":[93],"this":[94],"work,":[95],"we":[96],"introduce":[97],"an":[98],"automated":[99],"method":[100],"for":[101,156],"and":[104,113,119,136,176],"negative":[105,135],"in":[106],"cleaning,":[108],"based":[109],"on":[110],"Sherlock":[111,122,149,160],"rules":[112,123],"reference":[114,120],"tables.":[115],"tuple":[118],"tables,":[121],"tell":[124],"us":[125],"what":[126,131],"attributes":[127,132],"are":[128,133],"positive,":[130],"(possibly)":[137],"update":[140],"them.":[141],"We":[142,151,162],"study":[143],"several":[144],"problems":[146],"associated":[147],"with":[148,173],"rules.":[150,161],"also":[152,179],"present":[153],"efficient":[154],"algorithms":[155],"experimentally":[163],"demonstrate":[164],"our":[166],"techniques":[167],"can":[168],"not":[169],"only":[170],"annotate":[171],"negative,":[177],"but":[178],"repair":[180],"when":[182],"enough":[183],"information":[184],"available.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}