{"id":"https://openalex.org/W2123767107","doi":"https://doi.org/10.1145/1081870.1081916","title":"Finding similar files in large document repositories","display_name":"Finding similar files in large document repositories","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2123767107","doi":"https://doi.org/10.1145/1081870.1081916","mag":"2123767107"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081916","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077348567","display_name":"George Forman","orcid":"https://orcid.org/0000-0003-2179-4930"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Forman","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA","Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088426443","display_name":"Kave Eshghi","orcid":"https://orcid.org/0000-0003-3374-3145"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kave Eshghi","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA","Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049475725","display_name":"Stephane Chiocchetti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086826","display_name":"Hewlett-Packard (France)","ror":"https://ror.org/00497h462","country_code":"FR","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210086826"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stephane Chiocchetti","raw_affiliation_strings":["Hewlett-Packard France, Courtaboeuf, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard France, Courtaboeuf, France","institution_ids":["https://openalex.org/I4210086826"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7655,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.86742167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"394","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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":0.9994000196456909,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9991999864578247,"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":0.857097327709198},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.601926326751709},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5621837973594666},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.507668137550354},{"id":"https://openalex.org/keywords/document-management-system","display_name":"Document management system","score":0.4685923457145691},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4409295320510864},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43951311707496643},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4252609312534332},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11893782019615173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.857097327709198},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.601926326751709},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5621837973594666},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.507668137550354},{"id":"https://openalex.org/C2278759","wikidata":"https://www.wikidata.org/wiki/Q831677","display_name":"Document management system","level":2,"score":0.4685923457145691},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4409295320510864},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43951311707496643},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4252609312534332},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11893782019615173}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1081870.1081916","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.386.8067","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.8067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/kdd05/docs/p394.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.84.5107","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.5107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/techreports/2005/HPL-2005-42R1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1609518033","https://openalex.org/W2007842132","https://openalex.org/W2056980397","https://openalex.org/W2152565070","https://openalex.org/W2161532103","https://openalex.org/W2914888117","https://openalex.org/W4285719527","https://openalex.org/W6606280768","https://openalex.org/W6636190696"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W188202134","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W4255934811","https://openalex.org/W3181407718","https://openalex.org/W2346748597"],"abstract_inverted_index":{"Hewlett-Packard":[0],"has":[1],"many":[2],"millions":[3],"of":[4,11,15,42,50,73,140,146],"technical":[5,62],"support":[6,36],"documents":[7,37,75,89],"in":[8,135],"a":[9,83],"variety":[10],"collections.":[12],"As":[13],"part":[14],"content":[16,93],"management,":[17],"such":[18],"collections":[19],"are":[20,39,76],"periodically":[21],"merged":[22],"and":[23,33,58,68],"groomed.":[24],"In":[25],"the":[26,48,51,71,124,141],"process,":[27],"it":[28],"becomes":[29],"important":[30],"to":[31,115,127,158],"identify":[32,87],"weed":[34],"out":[35],"that":[38,65,85,112,131],"largely":[40],"duplicates":[41],"newer":[43],"versions.":[44],"Doing":[45],"so":[46],"improves":[47,59],"quality":[49],"collection,":[52],"eliminates":[53],"chaff":[54],"from":[55],"search":[56],"results,":[57],"customer":[60],"satisfaction.The":[61],"challenge":[63],"is":[64,78,120],"through":[66],"workflow":[67],"human":[69],"processes,":[70],"knowledge":[72],"which":[74,99],"related":[77,147],"often":[79],"lost.":[80],"We":[81],"required":[82],"method":[84],"could":[86],"similar":[88,110],"based":[90,121],"on":[91,97,122],"their":[92],"alone,":[94],"without":[95],"relying":[96],"metadata,":[98],"may":[100,132],"be":[101,133,156],"corrupt":[102],"or":[103],"missing.We":[104],"present":[105],"an":[106],"approach":[107],"for":[108],"finding":[109],"files":[111],"scales":[113],"up":[114],"large":[116],"document":[117],"repositories.":[118],"It":[119],"chunking":[123],"byte":[125],"stream":[126],"find":[128],"unique":[129],"signatures":[130],"shared":[134],"multiple":[136],"files.":[137,148],"An":[138,149],"analysis":[139],"file-chunk":[142],"graph":[143,152],"yields":[144],"clusters":[145],"optional":[150],"bipartite":[151],"partitioning":[153],"algorithm":[154],"can":[155],"applied":[157],"greatly":[159],"increase":[160],"scalability.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
