{"id":"https://openalex.org/W4393180082","doi":"https://doi.org/10.1145/3639303","title":"Determining the Largest Overlap between Tables","display_name":"Determining the Largest Overlap between Tables","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4393180082","doi":"https://doi.org/10.1145/3639303"},"language":"en","primary_location":{"id":"doi:10.1145/3639303","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639303","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639303","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061991280","display_name":"Luca Zecchini","orcid":"https://orcid.org/0000-0002-4856-0838"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Zecchini","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"raw_orcid":"https://orcid.org/0000-0002-4856-0838","affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042896292","display_name":"Tobias Bleifu\u00df","orcid":"https://orcid.org/0009-0006-9517-7707"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Bleifu\u00df","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"raw_orcid":"https://orcid.org/0009-0006-9517-7707","affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047630333","display_name":"Giovanni Simonini","orcid":"https://orcid.org/0000-0002-3466-509X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Simonini","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3466-509X","affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037830808","display_name":"Sonia Bergamaschi","orcid":"https://orcid.org/0000-0001-8087-6587"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sonia Bergamaschi","raw_affiliation_strings":["University of Modena and Reggio Emilia, Modena, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8087-6587","affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso Plattner Institute, University of Potsdam, Potsdam, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4483-1389","affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute, University of Potsdam, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1926,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78895804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"26"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7827291488647461},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6775535941123962},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5987452864646912},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5676873326301575},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.5492349863052368},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4957972466945648},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4526387155056},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37469571828842163},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34004998207092285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25654029846191406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827291488647461},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6775535941123962},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5987452864646912},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5676873326301575},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.5492349863052368},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4957972466945648},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4526387155056},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37469571828842163},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34004998207092285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25654029846191406},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3639303","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639303","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639303","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:iris.unimore.it:11380/1335869","is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1335869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"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:10.1145/3639303","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639303","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639303","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311022","display_name":"Universit\u00e0 Degli Studi di Modena e Reggio Emila","ror":"https://ror.org/02d4c4y02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393180082.pdf","grobid_xml":"https://content.openalex.org/works/W4393180082.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1492403551","https://openalex.org/W1521736627","https://openalex.org/W1544441076","https://openalex.org/W1549531352","https://openalex.org/W1969621019","https://openalex.org/W1970663544","https://openalex.org/W2020022499","https://openalex.org/W2035274534","https://openalex.org/W2099725016","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2123845384","https://openalex.org/W2132022258","https://openalex.org/W2140116426","https://openalex.org/W2153225416","https://openalex.org/W2159186077","https://openalex.org/W2182148130","https://openalex.org/W2290320465","https://openalex.org/W2341748398","https://openalex.org/W2606791715","https://openalex.org/W2741470040","https://openalex.org/W2752618741","https://openalex.org/W2795089200","https://openalex.org/W2798412430","https://openalex.org/W2798664493","https://openalex.org/W2899286282","https://openalex.org/W2903025523","https://openalex.org/W2948163032","https://openalex.org/W2963174348","https://openalex.org/W2970920572","https://openalex.org/W2970992672","https://openalex.org/W2971681342","https://openalex.org/W2988782038","https://openalex.org/W3014616325","https://openalex.org/W3031051334","https://openalex.org/W3032215537","https://openalex.org/W3035231859","https://openalex.org/W3085477028","https://openalex.org/W3102264439","https://openalex.org/W3103177583","https://openalex.org/W3174380000","https://openalex.org/W3174637548","https://openalex.org/W4205922070","https://openalex.org/W4229641819","https://openalex.org/W4231955481","https://openalex.org/W4235234911","https://openalex.org/W4240301789","https://openalex.org/W4283383705","https://openalex.org/W4310390625","https://openalex.org/W4321448337","https://openalex.org/W4365456672","https://openalex.org/W4380433179","https://openalex.org/W4383988293","https://openalex.org/W6929607700"],"related_works":["https://openalex.org/W4281971614","https://openalex.org/W2131131934","https://openalex.org/W1519332147","https://openalex.org/W4226523698","https://openalex.org/W2070384782","https://openalex.org/W3087250444","https://openalex.org/W4385281412","https://openalex.org/W4206785508","https://openalex.org/W2726157743","https://openalex.org/W2414530304"],"abstract_inverted_index":{"Both":[0],"on":[1,196,212],"the":[2,17,38,41,46,71,81,84,97,108,115,123,128,167,171,187],"Web":[3],"and":[4,33,89,125,178,208],"in":[5,16,77,103,122,201],"data":[6,15,146],"lakes,":[7],"it":[8,180],"is":[9,30,51,65],"possible":[10],"to":[11,86,141,153,156,162,184],"detect":[12,186],"much":[13],"redundant":[14],"form":[18],"of":[19,23,40,80,96,110,114,127,175],"largely":[20],"overlapping":[21],"pairs":[22],"tables.":[24,42,192],"In":[25,54],"many":[26],"cases,":[27],"this":[28,176,203],"overlap":[29,47,73,99,189],"not":[31,52,75],"accidental":[32],"provides":[34],"significant":[35],"information":[36,72],"about":[37],"relatedness":[39],"Unfortunately,":[43],"efficiently":[44,185],"quantifying":[45],"between":[48,190],"two":[49,191],"tables":[50,137],"trivial.":[53],"particular,":[55],"detecting":[56,132],"their":[57,61,143],"largest":[58,62,98,188],"overlap,":[59],"i.e.,":[60],"common":[63],"subtable,":[64],"a":[66],"computationally":[67],"challenging":[68],"problem.":[69],"As":[70],"may":[74],"occur":[76],"contiguous":[78],"portions":[79],"tables,":[82],"only":[83],"ability":[85],"permute":[87],"columns":[88],"rows":[90],"can":[91,100,119],"reveal":[92],"it.":[93],"The":[94],"detection":[95],"help":[101],"us":[102,140],"relevant":[104],"tasks":[105],"such":[106],"as":[107],"discovery":[109],"multiple":[111,213],"coexisting":[112],"versions":[113],"same":[116],"table,":[117],"which":[118],"present":[120,170],"differences":[121],"completeness":[124],"correctness":[126],"conveyed":[129],"information.":[130],"Automatically":[131],"these":[133],"highly":[134],"similar,":[135],"matching":[136],"would":[138],"allow":[139],"guarantee":[142],"consistency":[144],"through":[145],"cleaning":[147],"or":[148,161],"change":[149],"propagation,":[150],"but":[151],"also":[152],"eliminate":[154],"redundancy":[155],"free":[157],"up":[158],"storage":[159],"space":[160],"save":[163],"additional":[164],"work":[165],"for":[166],"editors.":[168],"We":[169,193],"first":[172],"formal":[173],"definition":[174],"problem,":[177],"with":[179],"Sloth,":[181],"our":[182],"solution":[183],"experimentally":[194],"demonstrate":[195],"real-world":[197],"datasets":[198],"its":[199,206,210],"efficacy":[200],"solving":[202],"task,":[204],"analyzing":[205],"performance":[207],"showing":[209],"impact":[211],"use":[214],"cases.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}