{"id":"https://openalex.org/W2031101249","doi":"https://doi.org/10.1145/2661829.2661837","title":"Cleanix","display_name":"Cleanix","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2031101249","doi":"https://doi.org/10.1145/2661829.2661837","mag":"2031101249"},"language":"en","primary_location":{"id":"doi:10.1145/2661829.2661837","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2661837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","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/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":true,"raw_author_name":"Hongzhi Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","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, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","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, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","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, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","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, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","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/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":"Jiacheng Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100396652"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.2175,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82034697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2024","last_page":"2026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9922999739646912,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7889219522476196},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.5538467764854431},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49094346165657043},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.44829443097114563},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.394480437040329},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27574622631073},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2426585555076599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889219522476196},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.5538467764854431},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49094346165657043},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.44829443097114563},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.394480437040329},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27574622631073},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2426585555076599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2661829.2661837","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2661837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G6080451938","display_name":null,"funder_award_id":"2012CB316200","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G984241737","display_name":null,"funder_award_id":"61472099","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1488893975","https://openalex.org/W1547556487","https://openalex.org/W2083541728","https://openalex.org/W2097745829","https://openalex.org/W2122465391","https://openalex.org/W2154915179"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2364420803"],"abstract_inverted_index":{"In":[0],"this":[1],"demo,":[2],"we":[3],"present":[4],"Cleanix,":[5],"a":[6,26,71],"prototype":[7],"system":[8,32],"for":[9],"cleaning":[10,50,80],"relational":[11],"Big":[12],"Data.":[13],"Cleanix":[14,46,69],"takes":[15],"data":[16,20,49,60,79],"integrated":[17],"from":[18],"multiple":[19],"sources":[21],"and":[22,38,57,63,77],"cleans":[23],"them":[24],"on":[25],"shared-nothing":[27],"machine":[28],"cluster.":[29],"The":[30],"backend":[31],"is":[33,70],"built":[34],"on-top-of":[35],"an":[36],"extensible":[37],"flexible":[39],"data-parallel":[40],"substrate":[41],"-":[42],"the":[43,82],"Hyracks":[44],"framework.":[45],"supports":[47,75],"various":[48],"tasks":[51],"such":[52],"as":[53],"abnormal":[54],"value":[55],"detection":[56],"correction,":[58],"incomplete":[59],"filling,":[61],"de-duplication,":[62],"conflict":[64],"resolution.":[65],"We":[66],"demonstrate":[67],"that":[68,74],"practical":[72],"tool":[73],"effective":[76],"efficient":[78],"at":[81],"large":[83],"scale.":[84]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
