{"id":"https://openalex.org/W2190899134","doi":"https://doi.org/10.14778/2850578.2850579","title":"Messing up with BART","display_name":"Messing up with BART","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2190899134","doi":"https://doi.org/10.14778/2850578.2850579","mag":"2190899134"},"language":"en","primary_location":{"id":"doi:10.14778/2850578.2850579","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2850578.2850579","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/A5079836420","display_name":"Patricia C. Arocena","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Patricia C. Arocena","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061858093","display_name":"Boris Glavic","orcid":"https://orcid.org/0000-0003-2887-2452"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Glavic","raw_affiliation_strings":["Illinois Inst. of Technology"],"affiliations":[{"raw_affiliation_string":"Illinois Inst. of Technology","institution_ids":["https://openalex.org/I180949307"]}]},{"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":["University of Basilicata, Italy"],"affiliations":[{"raw_affiliation_string":"University of Basilicata, Italy","institution_ids":["https://openalex.org/I20272500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ren\u00e9e J. Miller","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"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/I4210138380","display_name":"Qatar Cardiovascular Research Center","ror":"https://ror.org/038vyt185","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210138380"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Paolo Papotti","raw_affiliation_strings":["QCRI Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"QCRI Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]},{"author_position":"last","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":["University of Basilicata, Italy"],"affiliations":[{"raw_affiliation_string":"University of Basilicata, Italy","institution_ids":["https://openalex.org/I20272500"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079836420"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":7.3861,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.97031401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"9","issue":"2","first_page":"36","last_page":"47"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9959999918937683,"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/scalability","display_name":"Scalability","score":0.7827781438827515},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7436788082122803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.73933345079422},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7143381834030151},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.6055951714515686},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.5408627986907959},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4924820363521576},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47717538475990295},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.47633296251296997},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4398627281188965},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4352865219116211},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3633062243461609},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29348301887512207},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2453233003616333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15974831581115723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13287672400474548},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10640445351600647}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7827781438827515},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7436788082122803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73933345079422},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7143381834030151},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.6055951714515686},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.5408627986907959},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4924820363521576},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47717538475990295},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.47633296251296997},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4398627281188965},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4352865219116211},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3633062243461609},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29348301887512207},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2453233003616333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15974831581115723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13287672400474548},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10640445351600647},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2850578.2850579","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2850578.2850579","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"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":27,"referenced_works":["https://openalex.org/W1497367751","https://openalex.org/W1964929381","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2047745978","https://openalex.org/W2048372226","https://openalex.org/W2048864522","https://openalex.org/W2078132546","https://openalex.org/W2089206172","https://openalex.org/W2099637074","https://openalex.org/W2110993096","https://openalex.org/W2112840274","https://openalex.org/W2113582770","https://openalex.org/W2117854600","https://openalex.org/W2131060875","https://openalex.org/W2136709660","https://openalex.org/W2137775416","https://openalex.org/W2153531471","https://openalex.org/W2161163216","https://openalex.org/W2164636932","https://openalex.org/W2166709576","https://openalex.org/W2167333415","https://openalex.org/W2171332293","https://openalex.org/W2188696002","https://openalex.org/W2229256087","https://openalex.org/W6679898556","https://openalex.org/W6680599078"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W1605933025","https://openalex.org/W2963994172","https://openalex.org/W2499743893"],"abstract_inverted_index":{"We":[0,46],"study":[1],"the":[2,11,24,31,36,49,52,90,113,118],"problem":[3,54],"of":[4,13,28,88,102,117],"introducing":[5],"errors":[6],"into":[7],"clean":[8],"databases":[9],"for":[10],"purpose":[12],"benchmarking":[14],"data-cleaning":[15],"algorithms.":[16],"Our":[17],"goal":[18],"is":[19,55,112],"to":[20,43,86],"provide":[21,63],"users":[22],"with":[23],"highest":[25],"possible":[26],"level":[27],"control":[29,109],"over":[30],"error-generation":[32,53],"process,":[33],"and":[34,58,71,110],"at":[35],"same":[37],"time":[38],"develop":[39,68],"solutions":[40],"that":[41,51,75],"scale":[42,85],"large":[44],"databases.":[45],"show":[47],"in":[48,59],"paper":[50],"surprisingly":[56],"challenging,":[57],"fact,":[60],"NP-complete.":[61],"To":[62,84],"a":[64,69,98],"scalable":[65],"solution,":[66],"we":[67],"correct":[70],"efficient":[72],"greedy":[73],"algorithm":[74,91],"sacrifices":[76],"completeness,":[77],"but":[78],"succeeds":[79],"under":[80],"very":[81],"reasonable":[82],"assumptions.":[83],"millions":[87],"tuples,":[89],"relies":[92],"on":[93],"several":[94],"non-trivial":[95],"optimizations,":[96],"including":[97],"new":[99],"symmetry":[100],"property":[101],"data":[103],"quality":[104],"constraints.":[105],"The":[106],"trade-off":[107],"between":[108],"scalability":[111],"main":[114],"technical":[115],"contribution":[116],"paper.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
