{"id":"https://openalex.org/W2063103859","doi":"https://doi.org/10.14778/1952376.1952378","title":"Guided data repair","display_name":"Guided data repair","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2063103859","doi":"https://doi.org/10.14778/1952376.1952378","mag":"2063103859"},"language":"en","primary_location":{"id":"doi:10.14778/1952376.1952378","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1952376.1952378","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/A5103524335","display_name":"Mohamed Yakout","orcid":null},"institutions":[{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Mohamed Yakout","raw_affiliation_strings":["Purdue University and Qatar Computing Research Institute, Qatar Foundation","Purdue University and Qatar Computing Research Institute, Qatar Foundation#TAB#"],"affiliations":[{"raw_affiliation_string":"Purdue University and Qatar Computing Research Institute, Qatar Foundation","institution_ids":["https://openalex.org/I92528248"]},{"raw_affiliation_string":"Purdue University and Qatar Computing Research Institute, Qatar Foundation#TAB#","institution_ids":["https://openalex.org/I92528248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089912733","display_name":"Ahmed K. Elmagarmid","orcid":"https://orcid.org/0000-0002-0044-458X"},"institutions":[{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed K. Elmagarmid","raw_affiliation_strings":["Qatar Computing Research Institute, Qatar Foundation","Qatar Computing Research Institute, Qatar Foundation#TAB#"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Qatar Foundation","institution_ids":["https://openalex.org/I92528248"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Qatar Foundation#TAB#","institution_ids":["https://openalex.org/I92528248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064439579","display_name":"Jennifer Neville","orcid":"https://orcid.org/0000-0001-8108-4899"},"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":"Jennifer Neville","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/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"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":"Mourad Ouzzani","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/A5000141065","display_name":"Ihab F. Ilyas","orcid":"https://orcid.org/0000-0001-9052-9714"},"institutions":[{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ihab F. Ilyas","raw_affiliation_strings":["","Qatar Computing Research Institute Qatar Foundation, University of Waterloo"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Qatar Computing Research Institute Qatar Foundation, University of Waterloo","institution_ids":["https://openalex.org/I92528248"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103524335"],"corresponding_institution_ids":["https://openalex.org/I92528248"],"apc_list":null,"apc_paid":null,"fwci":15.71,"has_fulltext":false,"cited_by_count":217,"citation_normalized_percentile":{"value":0.99203903,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"4","issue":"5","first_page":"279","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973999857902527,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8095723986625671},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6222504377365112},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6210766434669495},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5461023449897766},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5368770360946655},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48730504512786865},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.47215983271598816},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42049455642700195},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3421992063522339},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11586260795593262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095723986625671},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6222504377365112},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6210766434669495},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5461023449897766},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5368770360946655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48730504512786865},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.47215983271598816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42049455642700195},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3421992063522339},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11586260795593262},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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":2,"locations":[{"id":"doi:10.14778/1952376.1952378","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1952376.1952378","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"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1457","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/451","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W138745945","https://openalex.org/W1539265392","https://openalex.org/W1700279323","https://openalex.org/W1964786778","https://openalex.org/W1977245551","https://openalex.org/W2026140005","https://openalex.org/W2059009730","https://openalex.org/W2065000833","https://openalex.org/W2067566391","https://openalex.org/W2069897123","https://openalex.org/W2099594809","https://openalex.org/W2106895292","https://openalex.org/W2122410182","https://openalex.org/W2131060875","https://openalex.org/W2133409729","https://openalex.org/W2136709660","https://openalex.org/W2137775416","https://openalex.org/W2149228467","https://openalex.org/W2153531471","https://openalex.org/W2161163216","https://openalex.org/W2163600218","https://openalex.org/W2167333415","https://openalex.org/W2254184375","https://openalex.org/W2426031434","https://openalex.org/W2911964244","https://openalex.org/W4250102289","https://openalex.org/W4285719527","https://openalex.org/W6678087030","https://openalex.org/W6679898556","https://openalex.org/W6680599078"],"related_works":["https://openalex.org/W2152992791","https://openalex.org/W2112835755","https://openalex.org/W2349674371","https://openalex.org/W4291951920","https://openalex.org/W2963262648","https://openalex.org/W2097495471","https://openalex.org/W2385867212","https://openalex.org/W2135768893","https://openalex.org/W176219849","https://openalex.org/W3021414116"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,86],"present":[4],"GDR,":[5],"a":[6,116,150],"Guided":[7],"Data":[8],"Repair":[9],"framework":[10],"that":[11,38],"incorporates":[12],"user":[13,29,34,72,162,173],"feedback":[14,128],"in":[15,45,157],"the":[16,33,36,59,64,67,71,84,93,99,124,133,139,143,169,172,176],"cleaning":[17],"process":[18],"to":[19,42,55,63,112,122,131,136],"enhance":[20],"and":[21,57,91,135,153,175],"accelerate":[22],"existing":[23],"automatic":[24],"repair":[25,132],"techniques":[26],"while":[27],"minimizing":[28],"involvement.":[30],"GDR":[31,49,148],"consults":[32],"on":[35,73,119,149],"updates":[37,61,80,114],"are":[39],"most":[40],"likely":[41],"be":[43],"beneficial":[44],"improving":[46],"data":[47,158,178],"quality.":[48,179],"also":[50],"uses":[51],"machine":[52],"learning":[53,111],"methods":[54],"identify":[56],"apply":[58,109],"correct":[60],"directly":[62],"database":[65,134],"without":[66],"actual":[68],"involvement":[69],"of":[70,95,102,104],"these":[74,89],"specific":[75],"updates.":[76],"To":[77],"rank":[78],"potential":[79],"for":[81,142],"consultation":[82],"by":[83],"user,":[85],"first":[87],"group":[88,97,117],"repairs":[90],"quantify":[92],"utility":[94],"each":[96],"using":[98,160],"decision-theory":[100],"concept":[101],"value":[103],"information":[105],"(VOI).":[106],"We":[107,145,166],"then":[108],"active":[110],"order":[113],"within":[115],"based":[118],"their":[120],"ability":[121],"improve":[123],"learned":[125],"model.":[126,144],"User":[127],"is":[129],"used":[130],"adaptively":[137],"refine":[138],"training":[140],"set":[141],"empirically":[146],"evaluate":[147],"real-world":[151],"dataset":[152],"show":[154],"significant":[155],"improvement":[156],"quality":[159],"our":[161],"guided":[163],"repairing":[164],"process.":[165],"also,":[167],"assess":[168],"trade-off":[170],"between":[171],"efforts":[174],"resulting":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":38},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":27},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":5}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2016-06-24T00:00:00"}
