{"id":"https://openalex.org/W2100141119","doi":"https://doi.org/10.1145/2532443.2532446","title":"b-bit minwise hashing in practice","display_name":"b-bit minwise hashing in practice","publication_year":2013,"publication_date":"2013-10-23","ids":{"openalex":"https://openalex.org/W2100141119","doi":"https://doi.org/10.1145/2532443.2532446","mag":"2100141119"},"language":"en","primary_location":{"id":"doi:10.1145/2532443.2532446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2532443.2532446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Asia-Pacific Symposium on Internetware","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/A5100741315","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-8515-7773"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ping Li","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024993683","display_name":"Anshumali Shrivastava","orcid":"https://orcid.org/0000-0002-5042-2856"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshumali Shrivastava","raw_affiliation_strings":["Cornell University, Ithaca, NY","Cornell University (Ithaca, NY);"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University (Ithaca, NY);","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034735876","display_name":"Arnd Christian K\u00f6nig","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":"Arnd Christian K\u00f6nig","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100741315"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":1.9356,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88441594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7772409319877625},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7057688236236572},{"id":"https://openalex.org/keywords/consistent-hashing","display_name":"Consistent hashing","score":0.5363581776618958},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.526208221912384},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4945361316204071},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49386173486709595},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.49094322323799133},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.4648434519767761},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4555895924568176},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43071502447128296},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3566949963569641},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.17199450731277466},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.15414485335350037},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11333191394805908},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0986049473285675},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09123831987380981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772409319877625},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7057688236236572},{"id":"https://openalex.org/C56856351","wikidata":"https://www.wikidata.org/wiki/Q1757218","display_name":"Consistent hashing","level":5,"score":0.5363581776618958},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.526208221912384},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4945361316204071},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49386173486709595},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.49094322323799133},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.4648434519767761},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4555895924568176},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43071502447128296},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3566949963569641},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.17199450731277466},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.15414485335350037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11333191394805908},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0986049473285675},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09123831987380981},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2532443.2532446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2532443.2532446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Asia-Pacific Symposium on Internetware","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.942.518","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.942.518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ecommons.cornell.edu/bitstream/handle/1813/37986/a13-li.pdf?sequence%3D2","raw_type":"text"},{"id":"pmh:oai:ecommons.cornell.edu:1813/37986","is_oa":false,"landing_page_url":"https://hdl.handle.net/1813/37986","pdf_url":null,"source":{"id":"https://openalex.org/S4306400757","display_name":"eCommons (Cornell University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"preprint"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337366","display_name":"Division of Social and Economic Sciences","ror":"https://ror.org/02dz2hb46"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W200648432","https://openalex.org/W1537946535","https://openalex.org/W1546441687","https://openalex.org/W1851100088","https://openalex.org/W1970576786","https://openalex.org/W1991800036","https://openalex.org/W1993091968","https://openalex.org/W1998840390","https://openalex.org/W2003108016","https://openalex.org/W2031252661","https://openalex.org/W2035720976","https://openalex.org/W2053377618","https://openalex.org/W2068418796","https://openalex.org/W2070996757","https://openalex.org/W2102221597","https://openalex.org/W2112490010","https://openalex.org/W2118585731","https://openalex.org/W2124120298","https://openalex.org/W2125993116","https://openalex.org/W2126887541","https://openalex.org/W2130484710","https://openalex.org/W2132069633","https://openalex.org/W2140431670","https://openalex.org/W2142623206","https://openalex.org/W2144399314","https://openalex.org/W2145349611","https://openalex.org/W2147017814","https://openalex.org/W2147717514","https://openalex.org/W2151224499","https://openalex.org/W2152565070","https://openalex.org/W2168467811","https://openalex.org/W2169557227","https://openalex.org/W2169660454","https://openalex.org/W2183705191","https://openalex.org/W2397770138","https://openalex.org/W3000138670","https://openalex.org/W3001645704","https://openalex.org/W4214595027"],"related_works":["https://openalex.org/W2334522381","https://openalex.org/W2076162755","https://openalex.org/W4385382899","https://openalex.org/W1582935010","https://openalex.org/W2149143947","https://openalex.org/W2126795708","https://openalex.org/W2084899141","https://openalex.org/W2390631617","https://openalex.org/W2105130984","https://openalex.org/W4385261619"],"abstract_inverted_index":{"Minwise":[0],"hashing":[1,27,73],"is":[2],"a":[3,21,58],"standard":[4],"technique":[5],"in":[6,46],"the":[7,75],"context":[8],"of":[9,24,60,77],"search":[10,32,48],"for":[11,30,43],"approximating":[12],"set":[13],"similarities.":[14],"The":[15],"recent":[16],"work":[17],"[26,":[18],"32]":[19],"demonstrated":[20],"potential":[22],"use":[23],"b-bit":[25,71],"minwise":[26,72],"[23,":[28],"24]":[29],"efficient":[31],"and":[33,49],"learning":[34],"on":[35,57],"massive,":[36],"high-dimensional,":[37],"binary":[38],"data":[39,78],"(which":[40],"are":[41],"typical":[42],"many":[44],"applications":[45],"Web":[47],"text":[50],"mining).":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"focus":[56],"number":[59],"critical":[61],"issues":[62],"which":[63],"must":[64],"be":[65],"addressed":[66],"before":[67],"one":[68],"can":[69],"apply":[70],"to":[74],"volumes":[76],"often":[79],"used":[80],"industrial":[81],"applications.":[82]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}