{"id":"https://openalex.org/W2081037744","doi":"https://doi.org/10.1109/infcom.2010.5461965","title":"Efficient Similarity Estimation for Systems Exploiting Data Redundancy","display_name":"Efficient Similarity Estimation for Systems Exploiting Data Redundancy","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2081037744","doi":"https://doi.org/10.1109/infcom.2010.5461965","mag":"2081037744"},"language":"en","primary_location":{"id":"doi:10.1109/infcom.2010.5461965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcom.2010.5461965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Proceedings IEEE INFOCOM","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/A5054849628","display_name":"Kanat Tangwongsan","orcid":"https://orcid.org/0000-0001-9775-8165"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kanat Tangwongsan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073063099","display_name":"Himabindu Pucha","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Himabindu Pucha","raw_affiliation_strings":["IBM Research Almaden","IBM Research \u2013Almaden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Almaden","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Research \u2013Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085479490","display_name":"David G. Andersen","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David G. Andersen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052885090","display_name":"Michael Kaminsky","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Kaminsky","raw_affiliation_strings":["Intel Labs Pittsburgh","Intel Labs, Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs Pittsburgh","institution_ids":["https://openalex.org/I4210158342"]},{"raw_affiliation_string":"Intel Labs, Pittsburgh","institution_ids":["https://openalex.org/I4210158342"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9656,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96451918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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":0.8465040922164917},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7501888275146484},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6848480105400085},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6740961670875549},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.540033757686615},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47947773337364197},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4763234555721283},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.4694017469882965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24208927154541016},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13759130239486694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465040922164917},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7501888275146484},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6848480105400085},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6740961670875549},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.540033757686615},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47947773337364197},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4763234555721283},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.4694017469882965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24208927154541016},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13759130239486694},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/infcom.2010.5461965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infcom.2010.5461965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Proceedings IEEE INFOCOM","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:compsci-1059","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1059&context=compsci","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6605120","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.3271","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.3271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/~dga/papers/simest-infocom2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.7546","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.7546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Ektangwon/research/infocom10.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":39,"referenced_works":["https://openalex.org/W38366299","https://openalex.org/W89823361","https://openalex.org/W95464215","https://openalex.org/W239964209","https://openalex.org/W841409518","https://openalex.org/W1487493679","https://openalex.org/W1490390347","https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W1741747329","https://openalex.org/W1847423537","https://openalex.org/W1975868314","https://openalex.org/W1978855656","https://openalex.org/W1993865637","https://openalex.org/W2026839093","https://openalex.org/W2056980397","https://openalex.org/W2132069633","https://openalex.org/W2132627996","https://openalex.org/W2150676586","https://openalex.org/W2152565070","https://openalex.org/W2153171667","https://openalex.org/W4230308551","https://openalex.org/W4243055721","https://openalex.org/W4254857363","https://openalex.org/W6601562713","https://openalex.org/W6603735688","https://openalex.org/W6603915564","https://openalex.org/W6609205758","https://openalex.org/W6623663579","https://openalex.org/W6629429606","https://openalex.org/W6629455298","https://openalex.org/W6634463810","https://openalex.org/W6636190696","https://openalex.org/W6637764636","https://openalex.org/W6638825795","https://openalex.org/W6644964241","https://openalex.org/W6679663036","https://openalex.org/W6679804201","https://openalex.org/W6682471989"],"related_works":["https://openalex.org/W2002428578","https://openalex.org/W2897258045","https://openalex.org/W3005646551","https://openalex.org/W2018406690","https://openalex.org/W2072332896","https://openalex.org/W2951748633","https://openalex.org/W2057691131","https://openalex.org/W2542042335","https://openalex.org/W2952039693","https://openalex.org/W4280621979"],"abstract_inverted_index":{"Many":[0],"modern":[1],"systems":[2,10,82],"exploit":[3],"data":[4,12,27,76,130],"redundancy":[5],"to":[6,29,59,100,153,174],"improve":[7],"efficiency.":[8],"These":[9],"split":[11],"into":[13],"chunks,":[14],"generate":[15],"identifiers":[16,24],"for":[17,42,75,92],"each":[18],"of":[19,45,77,141,150],"them,":[20],"and":[21,159],"compare":[22],"the":[23,43,64,78,102,142,148,164],"among":[25],"other":[26,105],"items":[28,131],"identify":[30],"duplicate":[31],"chunks.":[32,62],"As":[33],"a":[34,39,137,179],"result,":[35],"chunk":[36,72,86,106,134,165,181],"size":[37,87,166,182],"becomes":[38],"critical":[40],"parameter":[41],"efficiency":[44],"these":[46,184],"systems:":[47],"it":[48],"trades":[49],"potentially":[50],"improved":[51],"similarity":[52,65,128],"detection":[53],"(smaller":[54],"chunks)":[55],"with":[56,70],"increased":[57],"overhead":[58],"represent":[60],"more":[61],"Unfortunately,":[63],"between":[66,129],"files":[67],"increases":[68],"unpredictably":[69],"smaller":[71],"sizes,":[73],"even":[74],"same":[79],"type.":[80],"Existing":[81],"often":[83],"pick":[84],"one":[85],"that":[88,125,163],"is":[89],"\"good":[90],"enough''":[91],"many":[93],"cases":[94],"because":[95],"they":[96],"lack":[97],"efficient":[98],"techniques":[99],"determine":[101],"benefits":[103],"at":[104,132],"sizes.":[107],"This":[108],"paper":[109],"addresses":[110],"this":[111],"deficiency":[112],"via":[113],"two":[114],"contributions:":[115],"(1)":[116],"we":[117,145],"present":[118],"multi-resolution":[119],"(MR)":[120],"handprinting,":[121],"an":[122],"application-independent":[123],"technique":[124],"efficiently":[126],"estimates":[127],"different":[133],"sizes":[135],"using":[136,178],"compact,":[138],"multi-size":[139],"representation":[140],"data;":[143],"(2)":[144],"then":[146],"evaluate":[147],"application":[149],"MR":[151,170],"handprints":[152,171],"workloads":[154],"from":[155],"peer-to-peer,":[156],"file":[157],"transfer,":[158],"storage":[160],"systems,":[161],"demonstrating":[162],"selection":[167],"enabled":[168],"by":[169],"can":[172],"lead":[173],"real":[175],"improvements":[176],"over":[177],"fixed":[180],"in":[183],"systems.":[185]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
