{"id":"https://openalex.org/W2481573984","doi":"https://doi.org/10.1145/2882903.2915242","title":"Interactive and Deterministic Data Cleaning","display_name":"Interactive and Deterministic Data Cleaning","publication_year":2016,"publication_date":"2016-06-14","ids":{"openalex":"https://openalex.org/W2481573984","doi":"https://doi.org/10.1145/2882903.2915242","mag":"2481573984"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2915242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11563/126452","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101752229","display_name":"Jian He","orcid":"https://orcid.org/0000-0003-4892-7852"},"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":true,"raw_author_name":"Jian He","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059057476","display_name":"Enzo Veltri","orcid":"https://orcid.org/0000-0001-9947-8909"},"institutions":[{"id":"https://openalex.org/I20272500","display_name":"University of Basilicata","ror":"https://ror.org/03tc05689","country_code":"IT","type":"education","lineage":["https://openalex.org/I20272500"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enzo Veltri","raw_affiliation_strings":["Universita della Basilicata, Potenza, Italy"],"affiliations":[{"raw_affiliation_string":"Universita della Basilicata, Potenza, Italy","institution_ids":["https://openalex.org/I20272500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042429991","display_name":"Donatello Santoro","orcid":"https://orcid.org/0000-0002-5651-8584"},"institutions":[{"id":"https://openalex.org/I20272500","display_name":"University of Basilicata","ror":"https://ror.org/03tc05689","country_code":"IT","type":"education","lineage":["https://openalex.org/I20272500"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Donatello Santoro","raw_affiliation_strings":["Universita della Basilicata, Potenza, Italy"],"affiliations":[{"raw_affiliation_string":"Universita della Basilicata, Potenza, Italy","institution_ids":["https://openalex.org/I20272500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"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":"Guoliang Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008291639","display_name":"Giansalvatore Mecca","orcid":"https://orcid.org/0000-0002-1189-1481"},"institutions":[{"id":"https://openalex.org/I20272500","display_name":"University of Basilicata","ror":"https://ror.org/03tc05689","country_code":"IT","type":"education","lineage":["https://openalex.org/I20272500"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giansalvatore Mecca","raw_affiliation_strings":["Universita della Basilicata, Potenza, Italy"],"affiliations":[{"raw_affiliation_string":"Universita della Basilicata, Potenza, Italy","institution_ids":["https://openalex.org/I20272500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011336242","display_name":"Paolo Papotti","orcid":"https://orcid.org/0000-0003-0651-4128"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paolo Papotti","raw_affiliation_strings":["Arizona State University"],"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"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, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101752229"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":13.285,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.98774225,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"893","last_page":"907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9926000237464905,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9873999953269958,"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":0.8287490010261536},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7709110975265503},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.5858554244041443},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4740737974643707},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45108941197395325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4022905230522156},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36747443675994873},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.367350310087204},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2059372067451477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287490010261536},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7709110975265503},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.5858554244041443},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4740737974643707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45108941197395325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4022905230522156},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36747443675994873},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.367350310087204},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2059372067451477},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2882903.2915242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unibas.it:11563/126452","is_oa":true,"landing_page_url":"https://hdl.handle.net/11563/126452","pdf_url":null,"source":{"id":"https://openalex.org/S4377196360","display_name":"CINECA IRIS Institutional Research Information System (University of Basilicata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20272500","host_organization_name":"University of Basilicata","host_organization_lineage":["https://openalex.org/I20272500"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unibas.it:11563/126452","is_oa":true,"landing_page_url":"https://hdl.handle.net/11563/126452","pdf_url":null,"source":{"id":"https://openalex.org/S4377196360","display_name":"CINECA IRIS Institutional Research Information System (University of Basilicata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20272500","host_organization_name":"University of Basilicata","host_organization_lineage":["https://openalex.org/I20272500"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W158123262","https://openalex.org/W255556494","https://openalex.org/W1485156179","https://openalex.org/W1494137514","https://openalex.org/W1556285385","https://openalex.org/W1573646728","https://openalex.org/W1592026026","https://openalex.org/W1899648442","https://openalex.org/W1964929381","https://openalex.org/W1967167578","https://openalex.org/W1976732638","https://openalex.org/W1980706971","https://openalex.org/W1997952460","https://openalex.org/W2008271340","https://openalex.org/W2012837162","https://openalex.org/W2041645394","https://openalex.org/W2044102377","https://openalex.org/W2046298800","https://openalex.org/W2049770245","https://openalex.org/W2051716170","https://openalex.org/W2057178786","https://openalex.org/W2057513751","https://openalex.org/W2063103859","https://openalex.org/W2077207253","https://openalex.org/W2078132546","https://openalex.org/W2081186682","https://openalex.org/W2089206172","https://openalex.org/W2096454106","https://openalex.org/W2099239777","https://openalex.org/W2100986433","https://openalex.org/W2102489964","https://openalex.org/W2106895292","https://openalex.org/W2113607096","https://openalex.org/W2114376731","https://openalex.org/W2147805208","https://openalex.org/W2151604269","https://openalex.org/W2152191782","https://openalex.org/W2153635508","https://openalex.org/W2161163216","https://openalex.org/W2162034534","https://openalex.org/W2167333415","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2182787248","https://openalex.org/W2188696002","https://openalex.org/W2190899134","https://openalex.org/W2241277057","https://openalex.org/W2245236296","https://openalex.org/W3000214033","https://openalex.org/W4213009134","https://openalex.org/W6606395842","https://openalex.org/W6677117663","https://openalex.org/W6686029465","https://openalex.org/W6990023262"],"related_works":["https://openalex.org/W2377402383","https://openalex.org/W2380835401","https://openalex.org/W2381912691","https://openalex.org/W2350381577","https://openalex.org/W2353618196","https://openalex.org/W2348074676","https://openalex.org/W2385033175","https://openalex.org/W2374043190","https://openalex.org/W2363298784","https://openalex.org/W4320802139"],"abstract_inverted_index":{"We":[0,114,204],"present":[1],"Falcon,":[2],"an":[3],"interactive,":[4],"deterministic,":[5],"and":[6,50,100,176,199,212],"declarative":[7],"data":[8,34,225],"cleaning":[9],"system,":[10],"which":[11],"uses":[12],"SQL":[13],"update":[14,68,93,149],"queries":[15,69,94],"as":[16,118],"the":[17,27,38,45,76,102,106,112,128,136,145,174,178,196,202],"language":[18],"to":[19,43,53,74,142,193,215],"repair":[20,75],"data.":[21,77,113],"Falcon":[22,61,134,170,218],"does":[23],"not":[24],"rely":[25],"on":[26],"existence":[28],"of":[29,32,65,91,109,147,190],"a":[30,63,89,119,122,188],"set":[31,64,90,146],"pre-defined":[33],"quality":[35],"rules.":[36],"On":[37],"contrary,":[39],"it":[40],"encourages":[41],"users":[42,141,223],"explore":[44],"data,":[46],"identify":[47],"possible":[48,66],"problems,":[49],"make":[51],"updates":[52,130],"fix":[54],"them.":[55],"Bootstrapped":[56],"by":[57,138],"one":[58],"user":[59],"update,":[60],"guesses":[62],"sql":[67,92,148],"that":[70,95,127,169,217],"can":[71,171,219],"be":[72],"used":[73],"The":[78],"main":[79],"technical":[80],"challenge":[81],"addressed":[82],"in":[83,87,98,111,121,224],"this":[84,116],"paper":[85],"consists":[86],"finding":[88],"is":[96,185],"minimal":[97],"size":[99],"at":[101],"same":[103],"time":[104],"fixes":[105],"largest":[107],"number":[108,189],"errors":[110],"formalize":[115],"problem":[117],"search":[120,166,179,183,197],"lattice-shaped":[123],"space.":[124],"To":[125],"guarantee":[126],"chosen":[129],"are":[131],"semantically":[132],"correct,":[133],"navigates":[135],"lattice":[137,175],"interacting":[139],"with":[140,187,222],"gradually":[143],"validate":[144],"queries.":[150],"Besides":[151],"using":[152,209],"traditional":[153],"one-hop":[154],"based":[155],"traverse":[156],"algorithms":[157,167],"(e.g.,":[158],"BFS":[159],"or":[160],"DFS),":[161],"we":[162],"describe":[163],"novel":[164,182],"multi-hop":[165],"such":[168],"dive":[172],"over":[173],"conduct":[177],"efficiently.":[180],"Our":[181],"strategy":[184],"coupled":[186],"optimization":[191],"techniques":[192],"further":[194],"prune":[195],"space":[198],"efficiently":[200],"maintain":[201],"lattice.":[203],"have":[205],"conducted":[206],"extensive":[207],"experiments":[208],"both":[210],"real-world":[211],"synthetic":[213],"datasets":[214],"show":[216],"effectively":[220],"communicate":[221],"repairing.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
