{"id":"https://openalex.org/W4407583672","doi":"https://doi.org/10.1145/3712205","title":"Cleaning data with Swipe","display_name":"Cleaning data with Swipe","publication_year":2025,"publication_date":"2025-02-14","ids":{"openalex":"https://openalex.org/W4407583672","doi":"https://doi.org/10.1145/3712205"},"language":"en","primary_location":{"id":"doi:10.1145/3712205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712205","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://doi.org/10.1145/3712205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067359675","display_name":"Toon Boeckling","orcid":"https://orcid.org/0000-0002-4972-5294"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Toon Boeckling","raw_affiliation_strings":["Telecommunications and Information Processing, Ghent University, Gent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-4972-5294","affiliations":[{"raw_affiliation_string":"Telecommunications and Information Processing, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063611538","display_name":"Antoon Bronselaer","orcid":"https://orcid.org/0000-0001-6663-192X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Antoon Bronselaer","raw_affiliation_strings":["Telecommunications and Information Processing, Ghent University, Gent, Belgium","Telecommunications and Information Processing, Ghent University, Gent Belgium"],"raw_orcid":"https://orcid.org/0000-0001-6663-192X","affiliations":[{"raw_affiliation_string":"Telecommunications and Information Processing, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Telecommunications and Information Processing, Ghent University, Gent Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":2.1928,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85883094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"1","last_page":"29"},"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":0.9951000213623047,"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":0.9943000078201294,"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/swipe","display_name":"SwIPe","score":0.9575260877609253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.689683735370636},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3014112412929535}],"concepts":[{"id":"https://openalex.org/C2779623668","wikidata":"https://www.wikidata.org/wiki/Q7652842","display_name":"SwIPe","level":2,"score":0.9575260877609253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689683735370636},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3014112412929535}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3712205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712205","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},{"id":"pmh:oai:archive.ugent.be:01JPSB8W1T9G5NEQ0D94ZDD5B3","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01JPSB8W1T9G5NEQ0D94ZDD5B3","pdf_url":"https://biblio.ugent.be/publication/01JPSB8W1T9G5NEQ0D94ZDD5B3/file/01JPSB9TDR1MKY07CX08CZTT5Q.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1936-1963","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3712205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712205","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1563498062","https://openalex.org/W1976732638","https://openalex.org/W1986022261","https://openalex.org/W1992377735","https://openalex.org/W1992479406","https://openalex.org/W2009802499","https://openalex.org/W2022132320","https://openalex.org/W2028222220","https://openalex.org/W2032370604","https://openalex.org/W2044022210","https://openalex.org/W2044146725","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2047745978","https://openalex.org/W2054633003","https://openalex.org/W2063123613","https://openalex.org/W2073545563","https://openalex.org/W2077518845","https://openalex.org/W2081186682","https://openalex.org/W2089206172","https://openalex.org/W2099637074","https://openalex.org/W2112840274","https://openalex.org/W2153531471","https://openalex.org/W2167333415","https://openalex.org/W2251214202","https://openalex.org/W2437617937","https://openalex.org/W2475754495","https://openalex.org/W2591700809","https://openalex.org/W2901288224","https://openalex.org/W2948145720","https://openalex.org/W2960727496","https://openalex.org/W2962959301","https://openalex.org/W2983641625","https://openalex.org/W2995100136","https://openalex.org/W3004034804","https://openalex.org/W3082197983","https://openalex.org/W3105977086","https://openalex.org/W3191403450","https://openalex.org/W3197847098","https://openalex.org/W4220923188","https://openalex.org/W4223932145","https://openalex.org/W4240301789","https://openalex.org/W4293582904","https://openalex.org/W4312971344","https://openalex.org/W4385191118","https://openalex.org/W4399017998","https://openalex.org/W4401111747","https://openalex.org/W4401353630","https://openalex.org/W6969227564"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2398889655","https://openalex.org/W2536378363","https://openalex.org/W2549484948","https://openalex.org/W4205559861","https://openalex.org/W2158820730","https://openalex.org/W1547097662","https://openalex.org/W3202730707"],"abstract_inverted_index":{"The":[0,33,196],"repair":[1,41,54,108,163,203],"problem":[2,8],"for":[3,198,250,258],"functional":[4,20,79],"dependencies":[5,21,177],"is":[6,31,36,55,92,182,221,238],"the":[7,25,28,44,95,99,105,126,150,173,234],"where":[9],"an":[10,118,140,207,251,259],"input":[11],"database":[12,30,35],"needs":[13],"to":[14,60,103,193,223],"be":[15,159],"modified":[16],"such":[17,155],"that":[18,93,156,219,246],"all":[19],"are":[22,47,152,178,204],"satisfied":[23],"and":[24,81,110,168,187,201,231,256],"difference":[26],"with":[27],"original":[29],"minimal.":[32],"output":[34],"then":[37,50],"called":[38,183,209],"a":[39,52,67,146,190],"minimal-cost":[40,53,64],".":[42],"If":[43],"allowed":[45],"modifications":[46],"value":[48],"updates,":[49],"finding":[51],"NP-hard.":[56],"A":[57,86,242],"well-known":[58],"approach":[59,91],"find":[61],"approximations":[62],"of":[63,77,89,98,121,143,148,226,236,254,262],"repairs":[65,237],"builds":[66],"Chase":[68,100,127],"tree":[69,101,128],"in":[70,124,175,206],"which":[71,125,149,176],"each":[72,164],"internal":[73],"node":[74],"resolves":[75],"violations":[76],"one":[78,131,222],"dependency":[80],"leaf":[82],"nodes":[83],"represent":[84],"repairs.":[85],"key":[87],"property":[88],"this":[90,114,122,135],"controlling":[94],"branching":[96],"factor":[97],"allows":[102],"control":[104],"tradeoff":[106],"between":[107],"quality":[109,235],"computational":[111],"efficiency.":[112],"In":[113],"article,":[115],"we":[116,137,188],"explore":[117],"extreme":[119],"variant":[120],"idea":[123],"has":[129],"only":[130,166],"path.":[132],"To":[133],"construct":[134],"path,":[136],"first":[138],"create":[139],"ordered":[141],"partition":[142,147],"attributes":[144],"(i.e.,":[145],"classes":[151,157],"totally":[153],"ordered)":[154],"can":[158],"repaired":[160],"sequentially.":[161],"We":[162],"class":[165],"once":[167],"do":[169],"so":[170],"by":[171],"fixing":[172],"order":[174],"repaired.":[179],"This":[180],"principle":[181],"priority":[184,202],"repairing":[185],",":[186],"provide":[189],"simple":[191],"heuristic":[192],"determine":[194],"priority.":[195],"techniques":[197],"attribute":[199],"partitioning":[200],"combined":[205],"algorithm":[208],"Swipe.":[210],"An":[211],"empirical":[212],"study":[213],"on":[214],"four":[215],"real-life":[216],"datasets":[217],"shows":[218,245],"Swipe":[220,247],"three":[224],"orders":[225],"magnitude":[227],"faster":[228],"than":[229],"Llunatic":[230],"HoloClean,":[232],"whereas":[233],"comparable":[239],"or":[240],"better.":[241],"scalability":[243],"analysis":[244],"scales":[248],"linearly":[249],"increasing":[252,260],"number":[253,261],"tuples":[255],"quadratically":[257],"FDs.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-03T07:22:36.454288","created_date":"2025-10-10T00:00:00"}