{"id":"https://openalex.org/W4399017998","doi":"https://doi.org/10.1145/3665930","title":"BUNNI: Learning Repair Actions in Rule-driven Data Cleaning","display_name":"BUNNI: Learning Repair Actions in Rule-driven Data Cleaning","publication_year":2024,"publication_date":"2024-05-25","ids":{"openalex":"https://openalex.org/W4399017998","doi":"https://doi.org/10.1145/3665930"},"language":"en","primary_location":{"id":"doi:10.1145/3665930","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665930","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665930","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3665930","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["DIMIE, Universita degli Studi della Basilicata, Potenza, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1189-1481","affiliations":[{"raw_affiliation_string":"DIMIE, Universita degli Studi della Basilicata, Potenza, Italy","institution_ids":["https://openalex.org/I20272500"]}]},{"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/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paolo Papotti","raw_affiliation_strings":["EURECOM, Sophia Antipolis, France"],"raw_orcid":"https://orcid.org/0000-0003-0651-4128","affiliations":[{"raw_affiliation_string":"EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","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":["DiMIE, Universita degli Studi della Basilicata, Potenza, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5651-8584","affiliations":[{"raw_affiliation_string":"DiMIE, Universita degli Studi della Basilicata, Potenza, Italy","institution_ids":["https://openalex.org/I20272500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059057476","display_name":"Enzo Veltri","orcid":"https://orcid.org/0000-0001-9947-8909"},"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":"Enzo Veltri","raw_affiliation_strings":["Universita degli Studi della Basilicata, Potenza, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9947-8909","affiliations":[{"raw_affiliation_string":"Universita degli Studi della Basilicata, Potenza, Italy","institution_ids":["https://openalex.org/I20272500"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0304,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91229637,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"16","issue":"2","first_page":"1","last_page":"31"},"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":0.9984999895095825,"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":0.9796000123023987,"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/exploit","display_name":"Exploit","score":0.8463053703308105},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7736451625823975},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6972557306289673},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6390748620033264},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6245330572128296},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.622571587562561},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5813641548156738},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5788141489028931},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.49301740527153015},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4204399585723877},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.412234365940094},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38788482546806335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36494356393814087},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3332853317260742},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2331850230693817},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13209962844848633}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8463053703308105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736451625823975},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6972557306289673},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6390748620033264},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6245330572128296},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.622571587562561},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5813641548156738},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5788141489028931},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.49301740527153015},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4204399585723877},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.412234365940094},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38788482546806335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36494356393814087},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3332853317260742},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2331850230693817},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13209962844848633},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"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/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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3665930","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665930","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665930","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","raw_type":"journal-article"},{"id":"pmh:oai:iris.unibas.it:11563/180515","is_oa":true,"landing_page_url":"https://hdl.handle.net/11563/180515","pdf_url":"https://iris.unibas.it/bitstream/11563/180515/1/3665930.pdf","source":{"id":"https://openalex.org/S4377196360","display_name":"CINECA IRIS Institutional Research Information System (University of Basilicata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20272500","host_organization_name":"University of Basilicata","host_organization_lineage":["https://openalex.org/I20272500"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3665930","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3665930","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3665930","source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399017998.pdf","grobid_xml":"https://content.openalex.org/works/W4399017998.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1536741282","https://openalex.org/W1573646728","https://openalex.org/W1723619723","https://openalex.org/W1967167578","https://openalex.org/W1976732638","https://openalex.org/W1980706971","https://openalex.org/W1997952460","https://openalex.org/W2008271340","https://openalex.org/W2012837162","https://openalex.org/W2046298800","https://openalex.org/W2063103859","https://openalex.org/W2064766209","https://openalex.org/W2067566391","https://openalex.org/W2077518845","https://openalex.org/W2078132546","https://openalex.org/W2089206172","https://openalex.org/W2100986433","https://openalex.org/W2101705355","https://openalex.org/W2113607096","https://openalex.org/W2118365253","https://openalex.org/W2133990480","https://openalex.org/W2142472956","https://openalex.org/W2143075689","https://openalex.org/W2147805208","https://openalex.org/W2163614729","https://openalex.org/W2164187405","https://openalex.org/W2167333415","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2190899134","https://openalex.org/W2232417456","https://openalex.org/W2465178348","https://openalex.org/W2481573984","https://openalex.org/W2548122763","https://openalex.org/W2591700809","https://openalex.org/W2888804263","https://openalex.org/W2948145720","https://openalex.org/W2963341956","https://openalex.org/W2981852735","https://openalex.org/W2983641625","https://openalex.org/W3000214033","https://openalex.org/W3082197983","https://openalex.org/W3205626500","https://openalex.org/W4206723194","https://openalex.org/W4211029301","https://openalex.org/W4288089799","https://openalex.org/W4310390625","https://openalex.org/W4312092243","https://openalex.org/W4312157405","https://openalex.org/W4372267129","https://openalex.org/W4385284874","https://openalex.org/W4389609861","https://openalex.org/W6675204935","https://openalex.org/W6683456455"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2748020237","https://openalex.org/W2094985717"],"abstract_inverted_index":{"In":[0],"this":[1,121],"work,":[2],"we":[3,68],"address":[4],"the":[5,15,36,55,75,79,101,110],"challenging":[6],"and":[7,45,85,109],"open":[8],"problem":[9,18],"of":[10,26,38,40,52,57,63],"involving":[11],"non-expert":[12,58],"users":[13,42],"in":[14,103,134],"data":[16,34,46,65],"repairing":[17],"as":[19],"first-class":[20],"citizens.":[21],"Despite":[22],"a":[23,50,61,92,127],"large":[24],"number":[25],"proposals":[27],"that":[28,90,105,112],"have":[29],"been":[30],"devoted":[31],"to":[32,73,77,99,126],"cleaning":[33],"from":[35,54],"point":[37],"view":[39],"expert":[41],"(IT":[43],"staff":[44],"scientists),":[47],"there":[48],"is":[49,97],"lack":[51],"studies":[53],"perspective":[56],"ones.":[59],"Given":[60],"set":[62],"available":[64],"quality":[66,133],"rules,":[67],"exploit":[69],"machine":[70,122],"learning":[71,123],"techniques":[72],"guide":[74],"user":[76,94],"identify":[78,100],"dirty":[80],"values":[81,102],"for":[82],"each":[83],"violation":[84],"repair":[86],"them.":[87],"We":[88,117],"show":[89,118],"with":[91,131],"low":[93],"effort,":[95],"it":[96],"possible":[98],"tuples":[104],"can":[106],"be":[107],"trusted":[108],"ones":[111],"are":[113],"most":[114],"likely":[115],"errors.":[116],"experimentally":[119],"how":[120],"approach":[124],"leads":[125],"unique":[128],"clean":[129],"solution":[130],"high":[132],"scenarios":[135],"where":[136],"other":[137],"approaches":[138],"fail.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
