{"id":"https://openalex.org/W4394664657","doi":"https://doi.org/10.48550/arxiv.1103.3103","title":"Guided Data Repair","display_name":"Guided Data Repair","publication_year":2011,"publication_date":"2011-03-16","ids":{"openalex":"https://openalex.org/W4394664657","doi":"https://doi.org/10.48550/arxiv.1103.3103"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1103.3103","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1103.3103","pdf_url":"https://arxiv.org/pdf/1103.3103","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1103.3103","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103524335","display_name":"Mohamed Yakout","orcid":null,"observed_orcids":[]},"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":"Yakout, Mohamed","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0000-0002-0044-458X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elmagarmid, Ahmed K.","raw_affiliation_strings":["Qatar Computing Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064439579","display_name":"Jennifer Neville","orcid":"https://orcid.org/0000-0001-8108-4899","observed_orcids":["https://orcid.org/0000-0001-8108-4899","https://orcid.org/0009-0007-1157-018X"]},"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":"Neville, Jennifer","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"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","observed_orcids":["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":"Ouzzani, Mourad","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0000-0001-9052-9714"]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ilyas, Ihab F.","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9883000254631042,"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":0.9883000254631042,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0032999999821186066,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0020000000949949026,"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/data-repair","display_name":"data repair","score":0.6769999861717224},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.75},{"id":"https://openalex.org/keywords/user-feedback","display_name":"user feedback","score":0.9120000004768372},{"id":"https://openalex.org/keywords/value-of-information","display_name":"value of information","score":0.7979999780654907},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.9890000224113464},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.6759999990463257},{"id":"https://openalex.org/keywords/database-repair","display_name":"database repair","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37795695662498474}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1103.3103","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1103.3103","pdf_url":"https://arxiv.org/pdf/1103.3103","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1103.3103","doi":"https://doi.org/10.48550/arxiv.1103.3103","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1103.3103","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1103.3103","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1103.3103","pdf_url":"https://arxiv.org/pdf/1103.3103","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"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":[],"updated_date":"2026-10-03T13:16:28.481748","created_date":"2024-04-11T00:00:00"}