{"id":"https://openalex.org/W3197847098","doi":"https://doi.org/10.14778/3476249.3476301","title":"Horizon","display_name":"Horizon","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3197847098","doi":"https://doi.org/10.14778/3476249.3476301","mag":"3197847098"},"language":"en","primary_location":{"id":"doi:10.14778/3476249.3476301","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476301","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/A5004937696","display_name":"El Kindi Rezig","orcid":"https://orcid.org/0000-0002-5187-3499"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"El Kindi Rezig","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["Qatar Computing Research Institute"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000123743","display_name":"Walid G. Aref","orcid":"https://orcid.org/0000-0001-8169-7775"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walid G. Aref","raw_affiliation_strings":["Purdue University"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089912733","display_name":"Ahmed K. Elmagarmid","orcid":"https://orcid.org/0000-0002-0044-458X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed K. Elmagarmid","raw_affiliation_strings":["Qatar Computing Research Institute"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102753790","display_name":"Ahmed R. Mahmood","orcid":"https://orcid.org/0000-0002-8886-6364"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed R. Mahmood","raw_affiliation_strings":["Purdue University"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074724644","display_name":"Michael Stonebraker","orcid":"https://orcid.org/0000-0001-9184-9058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Stonebraker","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5004937696"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4692,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94571568,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"14","issue":"11","first_page":"2546","last_page":"2554"},"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":0.9943000078201294,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9800000190734863,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7798464298248291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7410324811935425},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.615362823009491},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.6041040420532227},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5838429927825928},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5333542823791504},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.526788055896759},{"id":"https://openalex.org/keywords/data-integrity","display_name":"Data integrity","score":0.455645889043808},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4456402659416199},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4355669319629669},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.41074544191360474},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3327024281024933},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2867969572544098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1927235722541809},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1479598581790924},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12577885389328003},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0911899209022522}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7798464298248291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410324811935425},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.615362823009491},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.6041040420532227},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5838429927825928},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5333542823791504},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.526788055896759},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.455645889043808},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4456402659416199},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4355669319629669},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.41074544191360474},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3327024281024933},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2867969572544098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1927235722541809},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1479598581790924},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12577885389328003},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0911899209022522},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3476249.3476301","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476301","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":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1573646728","https://openalex.org/W1595443289","https://openalex.org/W1975184797","https://openalex.org/W2041442195","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2047745978","https://openalex.org/W2081186682","https://openalex.org/W2089206172","https://openalex.org/W2112840274","https://openalex.org/W2118382442","https://openalex.org/W2120220749","https://openalex.org/W2133409729","https://openalex.org/W2137775416","https://openalex.org/W2142472956","https://openalex.org/W2167333415","https://openalex.org/W2171332293","https://openalex.org/W2190899134","https://openalex.org/W2238711864","https://openalex.org/W2262592273","https://openalex.org/W2299844414","https://openalex.org/W2533303186","https://openalex.org/W2534652523","https://openalex.org/W2559785442","https://openalex.org/W2585438896","https://openalex.org/W2591700809","https://openalex.org/W2726342193","https://openalex.org/W2811353042","https://openalex.org/W2927176210","https://openalex.org/W2998574808","https://openalex.org/W3013864782","https://openalex.org/W3082197983","https://openalex.org/W4293582904"],"related_works":["https://openalex.org/W2891888580","https://openalex.org/W2215544391","https://openalex.org/W2906267174","https://openalex.org/W4210350690","https://openalex.org/W134501823","https://openalex.org/W2615656344","https://openalex.org/W2146933441","https://openalex.org/W3041894995","https://openalex.org/W2013239059","https://openalex.org/W2295626654"],"abstract_inverted_index":{"A":[0,16,218],"large":[1],"class":[2,18],"of":[3,19,43,83,104,144,208,220],"data":[4,37,44,57,68,95,105,137,155,188],"repair":[5,14,114,126,183,202,239],"algorithms":[6],"rely":[7],"on":[8,226],"integrity":[9],"constraints":[10,20],"to":[11,79,81,92,101,116,129,135,141,180,206],"detect":[12],"and":[13,62,74,98,162,177,210,229,241],"errors.":[15],"well-studied":[17],"is":[21,52,59,71,211],"Functional":[22],"Dependencies":[23],"(FDs,":[24],"for":[25,40],"short).":[26],"Although":[27],"there":[28],"has":[29,47],"been":[30,48],"an":[31,111],"increased":[32],"interest":[33],"in":[34,63,85,173,238],"developing":[35,67],"general":[36],"cleaning":[38,58,77,96,189,216,224],"systems":[39,55,190,225],"a":[41,181,200],"myriad":[42],"errors,":[45],"scalability":[46],"left":[49],"behind.":[50],"This":[51],"because":[53],"current":[54],"assume":[56],"performed":[60],"offline":[61],"one":[64],"iteration.":[65],"However,":[66],"science":[69],"pipelines":[70],"highly":[72],"iterative":[73],"requires":[75],"efficient":[76],"techniques":[78,127,237],"scale":[80],"millions":[82,207],"records":[84],"seconds/minutes,":[86],"not":[87],"days.":[88],"In":[89],"our":[90],"efforts":[91],"re-think":[93],"the":[94,102,136,151,154,159,168,174],"stack":[97],"bring":[99],"it":[100],"era":[103],"science,":[106],"we":[107],"introduce":[108],"Horizon":[109,149,198,221,233],",":[110],"end-to-end":[112],"FD":[113,125],"system":[115],"address":[117],"two":[118],"key":[119],"challenges:":[120],"(1)":[121],"Accuracy:":[122],"Most":[123],"existing":[124,236],"aim":[128],"produce":[130],"repairs":[131,165],"that":[132,138,166,204,232],"minimize":[133],"changes":[134],"may":[139],"lead":[140],"incorrect":[142],"combinations":[143],"attribute":[145],"values":[146],"(or":[147],"patterns).":[148],"leverages":[150],"interaction":[152],"between":[153],"patterns":[156,171],"induced":[157],"by":[158],"various":[160],"FDs,":[161],"subsequently":[163],"selects":[164],"preserve":[167],"most":[169],"frequent":[170],"found":[172],"original":[175],"data,":[176],"hence":[178],"leading":[179],"better":[182],"accuracy.":[184],"(2)":[185],"Scalability:":[186],"Existing":[187],"struggle":[191],"when":[192],"dealing":[193],"with":[194],"large-scale":[195],"real-world":[196],"datasets.":[197],"features":[199],"linear-time":[201],"algorithm":[203],"scales":[205],"records,":[209],"orders-of-magnitude":[212],"faster":[213],"than":[214],"state-of-the-art":[215,223],"algorithms.":[217],"benchmark":[219],"against":[222],"multiple":[227],"datasets":[228],"metrics":[230],"shows":[231],"consistently":[234],"outperforms":[235],"quality":[240],"scalability.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2021-09-13T00:00:00"}