{"id":"https://openalex.org/W2948145720","doi":"https://doi.org/10.1145/3299869.3324956","title":"Raha","display_name":"Raha","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2948145720","doi":"https://doi.org/10.1145/3299869.3324956","mag":"2948145720"},"language":"en","primary_location":{"id":"doi:10.1145/3299869.3324956","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299869.3324956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/137524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100690239","display_name":"Mohammad Mahdavi","orcid":"https://orcid.org/0000-0002-4171-7310"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mohammad Mahdavi","raw_affiliation_strings":["TU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009128577","display_name":"Ziawasch Abedjan","orcid":"https://orcid.org/0000-0002-2846-1373"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziawasch Abedjan","raw_affiliation_strings":["TU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003690515","display_name":"Raul Castro Fernandez","orcid":"https://orcid.org/0000-0001-7675-6080"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raul Castro Fernandez","raw_affiliation_strings":["MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110987"]}]},{"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/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":"Mourad Ouzzani","raw_affiliation_strings":["QCRI, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"QCRI, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074724644","display_name":"Michael Stonebraker","orcid":"https://orcid.org/0000-0001-9184-9058"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Stonebraker","raw_affiliation_strings":["MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110987"]}]},{"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/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":"Nan Tang","raw_affiliation_strings":["QCRI, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"QCRI, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100690239"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":9.6926,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.98251871,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"865","last_page":"882"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9952999949455261,"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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.7708538174629211},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6424661874771118},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5029553771018982},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5018212795257568},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4751206040382385},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.47088274359703064},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44832438230514526},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43989208340644836},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4046599864959717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3751635253429413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32887500524520874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14764446020126343},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0732620358467102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708538174629211},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6424661874771118},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5029553771018982},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5018212795257568},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4751206040382385},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.47088274359703064},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44832438230514526},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43989208340644836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4046599864959717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3751635253429413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32887500524520874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14764446020126343},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0732620358467102},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3299869.3324956","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299869.3324956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/137524","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137524","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"doi:10.5446/42905","is_oa":true,"landing_page_url":"https://doi.org/10.5446/42905","pdf_url":null,"source":{"id":"https://openalex.org/S7407052952","display_name":"TIB KMO / FLOWWORKS GmbH","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/137524","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/137524","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6052429835","display_name":null,"funder_award_id":"(DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8051084133","display_name":null,"funder_award_id":"387872445","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W760598031","https://openalex.org/W1531910981","https://openalex.org/W1532325895","https://openalex.org/W1592225892","https://openalex.org/W1595443289","https://openalex.org/W1610496399","https://openalex.org/W1673310716","https://openalex.org/W1678356000","https://openalex.org/W1680797894","https://openalex.org/W1992479406","https://openalex.org/W2008896880","https://openalex.org/W2028438572","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2063103859","https://openalex.org/W2064766209","https://openalex.org/W2101234009","https://openalex.org/W2113592823","https://openalex.org/W2113607096","https://openalex.org/W2114473442","https://openalex.org/W2123561513","https://openalex.org/W2132069633","https://openalex.org/W2162449239","https://openalex.org/W2165528679","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2190899134","https://openalex.org/W2298871042","https://openalex.org/W2401610261","https://openalex.org/W2427822648","https://openalex.org/W2439326083","https://openalex.org/W2481573984","https://openalex.org/W2496170334","https://openalex.org/W2542998387","https://openalex.org/W2544486974","https://openalex.org/W2548122763","https://openalex.org/W2549035799","https://openalex.org/W2560438049","https://openalex.org/W2562836854","https://openalex.org/W2585438896","https://openalex.org/W2591700809","https://openalex.org/W2803396353","https://openalex.org/W2875652255","https://openalex.org/W2962843773","https://openalex.org/W4213009331","https://openalex.org/W6636177537"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W2138823233","https://openalex.org/W1979740464","https://openalex.org/W2143345456","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W4315705795","https://openalex.org/W2101053337","https://openalex.org/W1870651561"],"abstract_inverted_index":{"Detecting":[0],"erroneous":[1],"values":[2,120],"is":[3,42],"a":[4,15,31,67,75,108],"key":[5],"step":[6],"in":[7,21],"data":[8,89,129],"cleaning.":[9],"Error":[10],"detection":[11,58,71,82,135,147],"algorithms":[12,59,83,136],"usually":[13],"require":[14],"user":[16,47],"to":[17,49,130],"provide":[18],"input":[19],"configurations":[20,37,79],"the":[22,46,53,56,117,144],"form":[23],"of":[24,36,78,88],"rules":[25],"or":[26],"statistical":[27],"parameters.":[28],"However,":[29],"providing":[30],"complete,":[32],"yet":[33],"correct,":[34],"set":[35],"for":[38,80,98,121],"each":[39,99,157],"new":[40,68],"dataset":[41,54],"not":[43],"trivial,":[44],"as":[45],"has":[48],"know":[50],"about":[51],"both":[52],"and":[55,111,137],"error":[57,70,81,134,146],"upfront.":[60],"In":[61,139],"this":[62],"paper,":[63],"we":[64,91,106],"present":[65],"Raha,":[66],"configuration-free":[69],"system.":[72],"By":[73],"generating":[74],"limited":[76],"number":[77],"that":[84,114],"cover":[85],"various":[86],"types":[87],"errors,":[90],"can":[92,126],"generate":[93],"an":[94],"expressive":[95],"feature":[96,104],"vector":[97],"tuple":[100],"value.":[101],"Leveraging":[102],"these":[103],"vectors,":[105],"propose":[107],"novel":[109],"sampling":[110],"classification":[112],"scheme":[113],"effectively":[115],"chooses":[116],"most":[118],"representative":[119],"training.":[122],"Furthermore,":[123],"our":[124,140],"system":[125],"exploit":[127],"historical":[128],"filter":[131],"out":[132],"irrelevant":[133],"configurations.":[138],"experiments,":[141],"Raha":[142],"outperforms":[143],"state-of-the-art":[145],"techniques":[148],"with":[149],"no":[150],"more":[151],"than":[152],"20":[153],"labeled":[154],"tuples":[155],"on":[156],"dataset.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-06-14T00:00:00"}