{"id":"https://openalex.org/W2103269600","doi":"https://doi.org/10.14778/1453856.1453935","title":"Cleaning uncertain data with quality guarantees","display_name":"Cleaning uncertain data with quality guarantees","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2103269600","doi":"https://doi.org/10.14778/1453856.1453935","mag":"2103269600"},"language":"en","primary_location":{"id":"doi:10.14778/1453856.1453935","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453935","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,"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 VLDB Endowment","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":"https://openalex.org/A5005847882","display_name":"Reynold Cheng","orcid":"https://orcid.org/0000-0002-9480-9809"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Reynold Cheng","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong","The Hong Kong Polytechnic University , Hung Hom, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"The Hong Kong Polytechnic University , Hung Hom, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062977790","display_name":"Jinchuan Chen","orcid":"https://orcid.org/0000-0001-6698-3052"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinchuan Chen","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong","The Hong Kong Polytechnic University , Hung Hom, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"The Hong Kong Polytechnic University , Hung Hom, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037366245","display_name":"Xike Xie","orcid":"https://orcid.org/0000-0001-5290-5408"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xike Xie","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong","The Hong Kong Polytechnic University , Hung Hom, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"The Hong Kong Polytechnic University , Hung Hom, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":10.7443,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.98353353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"722","last_page":"735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"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":0.9991000294685364,"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/T11106","display_name":"Data Management and Algorithms","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9873999953269958,"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/computer-science","display_name":"Computer science","score":0.755534827709198},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7286121845245361},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6627005338668823},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6385650038719177},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.606580376625061},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5629317164421082},{"id":"https://openalex.org/keywords/uncertain-data","display_name":"Uncertain data","score":0.5518204569816589},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5399717092514038},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47432228922843933},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4429115653038025},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42099636793136597},{"id":"https://openalex.org/keywords/range-query","display_name":"Range query (database)","score":0.41073736548423767},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39619386196136475},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3084034025669098},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.1758391559123993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16929343342781067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14172139763832092},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.13099750876426697},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.11220046877861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755534827709198},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7286121845245361},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6627005338668823},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6385650038719177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.606580376625061},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5629317164421082},{"id":"https://openalex.org/C2778865114","wikidata":"https://www.wikidata.org/wiki/Q7882489","display_name":"Uncertain data","level":2,"score":0.5518204569816589},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5399717092514038},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47432228922843933},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4429115653038025},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42099636793136597},{"id":"https://openalex.org/C136736807","wikidata":"https://www.wikidata.org/wiki/Q818943","display_name":"Range query (database)","level":5,"score":0.41073736548423767},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39619386196136475},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3084034025669098},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.1758391559123993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16929343342781067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14172139763832092},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.13099750876426697},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.11220046877861023},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/1453856.1453935","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453935","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,"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 VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.5883","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.5883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/1/1453935.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.226.6845","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.226.6845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.hku.hk/%7Eckcheng/papers/clean-vldb08.pdf","raw_type":"text"},{"id":"pmh:oai:hub.hku.hk:10722/61148","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/61148","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W137362001","https://openalex.org/W1482356393","https://openalex.org/W1491547607","https://openalex.org/W1541296334","https://openalex.org/W1550582582","https://openalex.org/W1599406659","https://openalex.org/W1796251476","https://openalex.org/W1977848225","https://openalex.org/W2013333366","https://openalex.org/W2033340210","https://openalex.org/W2041404167","https://openalex.org/W2041905826","https://openalex.org/W2044494469","https://openalex.org/W2078686663","https://openalex.org/W2085608749","https://openalex.org/W2088422262","https://openalex.org/W2090573020","https://openalex.org/W2097995023","https://openalex.org/W2099708664","https://openalex.org/W2102186495","https://openalex.org/W2108009586","https://openalex.org/W2110037957","https://openalex.org/W2118462151","https://openalex.org/W2125402103","https://openalex.org/W2125791539","https://openalex.org/W2138064798","https://openalex.org/W2138271690","https://openalex.org/W2138414767","https://openalex.org/W2138729760","https://openalex.org/W2142909274","https://openalex.org/W2165240468","https://openalex.org/W2166916904","https://openalex.org/W2166994031","https://openalex.org/W2171776999","https://openalex.org/W2993383518","https://openalex.org/W3111526966","https://openalex.org/W3145128584","https://openalex.org/W4285719527","https://openalex.org/W4391149753","https://openalex.org/W6648982606","https://openalex.org/W6672615329","https://openalex.org/W6680722260","https://openalex.org/W6684648153","https://openalex.org/W7029321148"],"related_works":["https://openalex.org/W2171943719","https://openalex.org/W50774052","https://openalex.org/W2340170180","https://openalex.org/W3108882786","https://openalex.org/W2098675459","https://openalex.org/W2574021396","https://openalex.org/W71851218","https://openalex.org/W2033626816","https://openalex.org/W2347240150","https://openalex.org/W2610943663"],"abstract_inverted_index":{"Uncertain":[0],"or":[1],"imprecise":[2],"data":[3,14,59,240],"are":[4,33,179],"pervasive":[5],"in":[6,80,87,174],"applications":[7],"like":[8],"location-based":[9],"services,":[10],"sensor":[11,58],"monitoring,":[12],"and":[13,16,30,146,188,200,230],"collection":[15],"integration.":[17],"For":[18,93],"these":[19],"applications,":[20],"probabilistic":[21,228],"databases":[22],"can":[23,122,196,236],"be":[24,78,123,197,237],"used":[25,238],"to":[26,35,50,61,77,82,169],"store":[27],"uncertain":[28,75],"data,":[29],"querying":[31],"facilities":[32],"provided":[34],"yield":[36],"answers":[37,112],"with":[38,209],"statistical":[39],"confidence.":[40],"Given":[41],"that":[42,106,133,149,192,201,221],"a":[43,103,166,223,227,234],"limited":[44],"amount":[45],"of":[46,70,74,90,110,137,140,153,157],"resources":[47],"is":[48,102,217],"available":[49],"\"clean\"":[51],"the":[52,68,72,84,88,98,108,114,135,151,154,158,193,218],"database":[53],"(e.g.,":[54,143,160],"by":[55],"probing":[56],"some":[57],"values":[60],"get":[62],"their":[63],"latest":[64],"values),":[65],"we":[66,96],"address":[67],"problem":[69],"choosing":[71],"set":[73],"objects":[76],"cleaned,":[79],"order":[81],"achieve":[83,170],"best":[85,214],"improvement":[86,173],"quality":[89,224],"query":[91,111,129],"answers.":[92],"this":[94,216],"purpose,":[95],"present":[97],"PWS-quality":[99,121,194],"metric,":[100],"which":[101],"universal":[104],"measure":[105],"quantifies":[107],"ambiguity":[109],"under":[113],"possible":[115],"world":[116],"semantics.":[117],"We":[118,163],"study":[119],"how":[120,232],"efficiently":[124],"evaluated":[125,198],"for":[126,226,239],"two":[127],"major":[128],"classes:":[130],"(1)":[131],"queries":[132,148],"examine":[134],"satisfiability":[136],"tuples":[138,142,159],"independent":[139],"other":[141],"range":[144],"queries);":[145],"(2)":[147],"require":[150],"knowledge":[152],"relative":[155],"ranking":[156],"MAX":[161],"queries).":[162],"then":[164],"propose":[165],"polynomial-time":[167],"solution":[168,208],"an":[171,206],"optimal":[172,207],"PWS-quality.":[175],"Other":[176],"fast":[177],"heuristics":[178],"presented":[180],"as":[181],"well.":[182],"Experiments,":[183],"performed":[184],"on":[185],"both":[186],"real":[187],"synthetic":[189],"datasets,":[190],"show":[191],"metric":[195,225,235],"quickly,":[199],"our":[202,213],"cleaning":[203,241],"algorithm":[204],"provides":[205],"high":[210],"efficiency.":[211],"To":[212],"knowledge,":[215],"first":[219],"work":[220],"develops":[222],"database,":[229],"investigates":[231],"such":[233],"purposes.":[242]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
