{"id":"https://openalex.org/W2128056631","doi":"https://doi.org/10.1145/1807167.1807267","title":"On indexing error-tolerant set containment","display_name":"On indexing error-tolerant set containment","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2128056631","doi":"https://doi.org/10.1145/1807167.1807267","mag":"2128056631"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075956031","display_name":"Parag Agrawal","orcid":"https://orcid.org/0009-0005-0759-8484"},"institutions":[{"id":"https://openalex.org/I1743320","display_name":"Palo Alto University","ror":"https://ror.org/04f812k67","country_code":"US","type":"education","lineage":["https://openalex.org/I1743320"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parag Agrawal","raw_affiliation_strings":["Stanford University, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1743320","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026802346","display_name":"Arvind Arasu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Arasu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103280746","display_name":"Raghav Kaushik","orcid":"https://orcid.org/0000-0003-1457-1384"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghav Kaushik","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0148,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.93695477,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"927","last_page":"938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T11106","display_name":"Data Management and Algorithms","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.984000027179718,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.9488011598587036},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.7570209503173828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111067771911621},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7009958028793335},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6554415225982666},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6340714693069458},{"id":"https://openalex.org/keywords/containment","display_name":"Containment (computer programming)","score":0.561687707901001},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5464822053909302},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49367818236351013},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4822441041469574},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4333757758140564},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4311123788356781},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42765137553215027},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31038445234298706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22734016180038452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21436133980751038},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.17811906337738037}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9488011598587036},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.7570209503173828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111067771911621},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7009958028793335},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6554415225982666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6340714693069458},{"id":"https://openalex.org/C2777019822","wikidata":"https://www.wikidata.org/wiki/Q390066","display_name":"Containment (computer programming)","level":2,"score":0.561687707901001},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5464822053909302},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49367818236351013},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4822441041469574},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4333757758140564},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4311123788356781},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42765137553215027},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31038445234298706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22734016180038452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21436133980751038},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.17811906337738037},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1807167.1807267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.750","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ilpubs.stanford.edu:8090/971/1/indexing.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1506285740","https://openalex.org/W1660390307","https://openalex.org/W1764756492","https://openalex.org/W1768336749","https://openalex.org/W1974995373","https://openalex.org/W2007682403","https://openalex.org/W2008235938","https://openalex.org/W2010454887","https://openalex.org/W2032866865","https://openalex.org/W2037594241","https://openalex.org/W2061779725","https://openalex.org/W2072173758","https://openalex.org/W2073540046","https://openalex.org/W2089326542","https://openalex.org/W2096598900","https://openalex.org/W2097704312","https://openalex.org/W2105436061","https://openalex.org/W2108991785","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2132069633","https://openalex.org/W2133953554","https://openalex.org/W2141469207","https://openalex.org/W2143182259","https://openalex.org/W2150546140","https://openalex.org/W2158779275","https://openalex.org/W2161936973","https://openalex.org/W2166559705","https://openalex.org/W2167029568","https://openalex.org/W2183705191","https://openalex.org/W6629956336","https://openalex.org/W6638104246","https://openalex.org/W6659738695","https://openalex.org/W6674576723","https://openalex.org/W6679663036","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2058987221","https://openalex.org/W2145657320","https://openalex.org/W2128056631","https://openalex.org/W2102493899","https://openalex.org/W1576730743","https://openalex.org/W2388346754","https://openalex.org/W4282568653","https://openalex.org/W2399928914","https://openalex.org/W2123678380","https://openalex.org/W180545237"],"abstract_inverted_index":{"Prior":[0],"work":[1,40],"has":[2],"identified":[3],"set":[4,33,48,71],"based":[5],"comparisons":[6],"as":[7,88],"a":[8,13,112],"useful":[9],"primitive":[10],"for":[11,58,81,154],"supporting":[12],"wide":[14],"variety":[15],"of":[16,32,39,47,70,125,138,160],"similarity":[17,34,63,76],"functions":[18],"in":[19,157],"record":[20],"matching.":[21],"Accordingly,":[22],"various":[23],"techniques":[24],"have":[25],"been":[26],"proposed":[27],"to":[28,78,93,121],"improve":[29],"the":[30,55,59,94,122,126,136,146,151,158],"performance":[31],"lookups.":[35],"However,":[36],"this":[37,51,75,144],"body":[38],"focuses":[41],"almost":[42],"exclusively":[43],"on":[44,107],"symmetric":[45],"notions":[46],"similarity.":[49],"In":[50],"paper,":[52],"we":[53],"study":[54],"indexing":[56,152],"problem":[57,153],"asymmetric":[60],"Jaccard":[61,155],"containment":[62,156],"function":[64,77],"that":[65,84,103,118,149],"is":[66,119,145],"an":[67,100],"error-tolerant":[68],"variation":[69],"containment.":[72],"We":[73,98],"enhance":[74],"also":[79],"account":[80],"string":[82,161],"transformations":[83],"reflect":[85],"synonyms":[86],"such":[87],"\"Bob\"":[89],"and":[90,111],"\"Robert\"":[91],"referring":[92],"same":[95],"first":[96,147],"name.":[97],"propose":[99],"index":[101,117],"structure":[102],"builds":[104],"inverted":[105],"lists":[106],"carefully":[108],"chosen":[109],"token-sets":[110],"lookup":[113],"algorithm":[114],"using":[115],"our":[116,139,142],"sensitive":[120],"output":[123],"size":[124],"query.":[127],"Our":[128],"experiments":[129],"over":[130],"real":[131],"life":[132],"data":[133],"sets":[134],"show":[135],"benefits":[137],"techniques.":[140],"To":[141],"knowledge,":[143],"paper":[148],"studies":[150],"presence":[159],"transformations.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}