{"id":"https://openalex.org/W2165528679","doi":"https://doi.org/10.1109/icde.2011.5767864","title":"Discovery of complex glitch patterns: A novel approach to Quantitative Data Cleaning","display_name":"Discovery of complex glitch patterns: A novel approach to Quantitative Data Cleaning","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2165528679","doi":"https://doi.org/10.1109/icde.2011.5767864","mag":"2165528679"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2011.5767864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","raw_type":"proceedings-article"},"type":"preprint","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/A5091872345","display_name":"Laure Berti\u2010\u00c9quille","orcid":"https://orcid.org/0000-0002-8046-0570"},"institutions":[{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Laure Berti-Equille","raw_affiliation_strings":["University of Rennes I, Rennes, France"],"affiliations":[{"raw_affiliation_string":"University of Rennes I, Rennes, France","institution_ids":["https://openalex.org/I56067802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086114454","display_name":"Tamraparni Dasu","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamraparni Dasu","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091872345"],"corresponding_institution_ids":["https://openalex.org/I56067802"],"apc_list":null,"apc_paid":null,"fwci":6.3588,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.96589984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"744"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9933000206947327,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.987500011920929,"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/glitch","display_name":"Glitch","score":0.8100301027297974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598618268966675},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7081137895584106},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.570743978023529},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5581828355789185},{"id":"https://openalex.org/keywords/extant-taxon","display_name":"Extant taxon","score":0.5358850359916687},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.4386656582355499},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4381803274154663},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20104697346687317},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0723540186882019}],"concepts":[{"id":"https://openalex.org/C191287063","wikidata":"https://www.wikidata.org/wiki/Q543281","display_name":"Glitch","level":3,"score":0.8100301027297974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598618268966675},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7081137895584106},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.570743978023529},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5581828355789185},{"id":"https://openalex.org/C178300618","wikidata":"https://www.wikidata.org/wiki/Q1898509","display_name":"Extant taxon","level":2,"score":0.5358850359916687},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.4386656582355499},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4381803274154663},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20104697346687317},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0723540186882019},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2011.5767864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01855785v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-01855785","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2011 IEEE International Conference on Data Engineering (ICDE 2011), Apr 2011, Hannover, Germany. ⟨10.1109/ICDE.2011.5767864⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W191253868","https://openalex.org/W199035648","https://openalex.org/W1481136135","https://openalex.org/W1550443206","https://openalex.org/W1551385575","https://openalex.org/W1563234575","https://openalex.org/W1987787956","https://openalex.org/W2026140005","https://openalex.org/W2064853889","https://openalex.org/W2108991785","https://openalex.org/W2119803607","https://openalex.org/W2150290224","https://openalex.org/W2153531471","https://openalex.org/W2164187405","https://openalex.org/W2187882913","https://openalex.org/W3146259567","https://openalex.org/W4252403066","https://openalex.org/W4300187280","https://openalex.org/W4300419544","https://openalex.org/W4300718545","https://openalex.org/W6633435546","https://openalex.org/W6677534882"],"related_works":["https://openalex.org/W2140328632","https://openalex.org/W17155033","https://openalex.org/W2541225405","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W2149184458","https://openalex.org/W4316660008","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274"],"abstract_inverted_index":{"Quantitative":[0],"Data":[1],"Cleaning":[2],"(QDC)":[3],"is":[4,86,128],"the":[5,69,72,81,91,103,140,159,164],"use":[6],"of":[7,31,41,71,96,107,110,163],"statistical":[8],"and":[9,16,50,94,105,135,138,161,171],"other":[10],"analytical":[11],"techniques":[12],"to":[13,112,154],"detect,":[14],"quantify,":[15],"correct":[17],"data":[18,32,42,99,148,173],"quality":[19],"problems":[20],"(or":[21],"glitches).":[22],"Current":[23],"QDC":[24,74],"approaches":[25],"focus":[26],"on":[27,167],"addressing":[28],"each":[29],"category":[30],"glitch":[33],"individually.":[34],"However,":[35],"in":[36,45,146],"real-world":[37,170],"data,":[38],"different":[39,108],"types":[40,109],"glitches":[43,53,111,137],"co-occur":[44],"complex":[46],"patterns.":[47],"These":[48],"patterns":[49],"interactions":[51,106],"between":[52],"offer":[54,119],"valuable":[55],"clues":[56],"for":[57,90,133],"developing":[58],"effective":[59],"domain-specific":[60],"quantitative":[61,141],"cleaning":[62,95,115,142],"strategies.":[63,124],"In":[64],"this":[65],"paper,":[66],"we":[67],"address":[68],"shortcomings":[70],"extant":[73],"methods":[75],"by":[76],"proposing":[77],"a":[78,87,129],"novel":[79],"framework,":[80],"DEC":[82,126,165],"(Detect-Explore-Clean)":[83],"framework.":[84],"It":[85],"comprehensive":[88],"approach":[89],"definition,":[92],"detection":[93],"complex,":[97],"multi-type":[98],"glitches.":[100],"We":[101,157],"exploit":[102],"distributions":[104],"develop":[113],"data-driven":[114],"strategies":[116,143],"that":[117,144,150],"may":[118],"significant":[120],"advantages":[121],"over":[122],"blind":[123],"The":[125],"framework":[127,166],"statistically":[130,152],"rigorous":[131],"methodology":[132],"evaluating":[134],"scoring":[136],"selecting":[139],"result":[145],"cleaned":[147],"sets":[149],"are":[151],"proximal":[153],"user":[155],"specifications.":[156],"demonstrate":[158],"efficacy":[160],"scalability":[162],"very":[168],"large":[169],"synthetic":[172],"sets.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}