{"id":"https://openalex.org/W2368635037","doi":"https://doi.org/10.1145/2935694.2935702","title":"Cleanix","display_name":"Cleanix","publication_year":2016,"publication_date":"2016-05-09","ids":{"openalex":"https://openalex.org/W2368635037","doi":"https://doi.org/10.1145/2935694.2935702","mag":"2368635037"},"language":"en","primary_location":{"id":"doi:10.1145/2935694.2935702","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2935694.2935702","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"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":"ACM SIGMOD Record","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/A5100396652","display_name":"Hongzhi Wang","orcid":"https://orcid.org/0000-0002-7521-2871"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Wang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101396650","display_name":"Mingda Li","orcid":"https://orcid.org/0009-0003-3693-8412"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingda Li","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102099238","display_name":"Yingyi Bu","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingyi Bu","raw_affiliation_strings":["University of California, Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387065","display_name":"Jianzhong Li","orcid":"https://orcid.org/0000-0002-4119-0571"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Li","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070851627","display_name":"Hong Gao","orcid":"https://orcid.org/0000-0002-2000-6683"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Gao","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100720453","display_name":"Jiacheng Zhang","orcid":"https://orcid.org/0000-0002-2311-7629"},"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":"Jiacheng Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8923,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91211108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"44","issue":"4","first_page":"35","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9750000238418579,"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":0.8841538429260254},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7212418913841248},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6751329898834229},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4696074426174164},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.45383715629577637},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4533093571662903},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4320053458213806},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3246074914932251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8841538429260254},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7212418913841248},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6751329898834229},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4696074426174164},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.45383715629577637},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4533093571662903},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4320053458213806},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3246074914932251},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2935694.2935702","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2935694.2935702","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"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":"ACM SIGMOD Record","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1488893975","https://openalex.org/W1536741282","https://openalex.org/W1547556487","https://openalex.org/W1610496399","https://openalex.org/W2031101249","https://openalex.org/W2043481183","https://openalex.org/W2073545563","https://openalex.org/W2083541728","https://openalex.org/W2097745829","https://openalex.org/W2108991785","https://openalex.org/W2137775416","https://openalex.org/W2140859480","https://openalex.org/W2153531471","https://openalex.org/W2154915179","https://openalex.org/W2167333415","https://openalex.org/W2400818018"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W12581771","https://openalex.org/W2891888580","https://openalex.org/W2215544391","https://openalex.org/W4253714063","https://openalex.org/W4210350690"],"abstract_inverted_index":{"For":[0],"big":[1],"data,":[2],"data":[3,10,37,41,69,80,93],"quality":[4],"problem":[5],"is":[6,54],"more":[7],"serious.":[8],"Big":[9,33],"cleaning":[11,31,70,94],"system":[12,29,53],"requires":[13],"scalability":[14],"and":[15,43,59,77,83],"the":[16,63,91,99],"abilityof":[17],"handling":[18],"mixed":[19],"errors.":[20],"Motivated":[21],"by":[22],"this,":[23],"we":[24,89],"develop":[25],"Cleanix,":[26],"a":[27,47],"prototype":[28],"for":[30],"relational":[32],"Data.":[34],"Cleanix":[35,66],"takes":[36],"integrated":[38],"from":[39],"multiple":[40],"sources":[42],"cleans":[44],"them":[45],"on":[46],"shared-nothing":[48],"machine":[49],"cluster.":[50],"The":[51],"backend":[52],"built":[55],"on-top-of":[56],"an":[57],"extensible":[58],"flexible":[60],"data-parallel":[61],"substrate":[62],"Hyracks":[64],"framework.":[65],"supports":[67],"various":[68],"tasks":[71],"such":[72],"as":[73,96,98],"abnormal":[74],"value":[75],"detection":[76],"correction,":[78],"incomplete":[79],"filling,":[81],"de-duplication,":[82],"conflict":[84],"resolution.":[85],"In":[86],"this":[87],"paper,":[88],"show":[90],"organization,":[92],"algorithms":[95],"well":[97],"design":[100],"of":[101],"Cleanix.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}
