{"id":"https://openalex.org/W318559539","doi":"https://doi.org/10.1109/laweb.2003.1250280","title":"On the evolution of clusters of near-duplicate Web pages","display_name":"On the evolution of clusters of near-duplicate Web pages","publication_year":2004,"publication_date":"2004-05-06","ids":{"openalex":"https://openalex.org/W318559539","doi":"https://doi.org/10.1109/laweb.2003.1250280","mag":"318559539"},"language":"en","primary_location":{"id":"doi:10.1109/laweb.2003.1250280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/laweb.2003.1250280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/LEOS 3rd International Conference on Numerical Simulation of Semiconductor Optoelectronic Devices (IEEE Cat. No.03EX726)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://research.microsoft.com/pubs/73807/laweb.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060832606","display_name":"Dennis Fetterly","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":true,"raw_author_name":"D. Fetterly","raw_affiliation_strings":["Microsoft Research Limited, Mountain View, CA, USA","[Microsoft Research, Mountain View, CA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research, Mountain View, CA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015555842","display_name":"Mark S. Manasse","orcid":"https://orcid.org/0000-0002-8981-8225"},"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":"M. Manasse","raw_affiliation_strings":["Microsoft Research Limited, Mountain View, CA, USA","[Microsoft Research, Mountain View, CA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research, Mountain View, CA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037200145","display_name":"Marc Najork","orcid":"https://orcid.org/0000-0003-1423-0854"},"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":"M. Najork","raw_affiliation_strings":["Microsoft Research Limited, Mountain View, CA, USA","[Microsoft Research, Mountain View, CA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research, Mountain View, CA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060832606"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.5781,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88067538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2","issue":"4","first_page":"37","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.984000027179718,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9758999943733215,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.8080692887306213},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6787623167037964},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6654398441314697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6476689577102661},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6180875301361084},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.532010555267334},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.5290994644165039},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.48190978169441223},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4564712941646576},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4528906047344208},{"id":"https://openalex.org/keywords/page-view","display_name":"Page view","score":0.42932868003845215},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.4159373342990875},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.29353123903274536}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8080692887306213},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6787623167037964},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6654398441314697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6476689577102661},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6180875301361084},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.532010555267334},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.5290994644165039},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.48190978169441223},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4564712941646576},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4528906047344208},{"id":"https://openalex.org/C103645729","wikidata":"https://www.wikidata.org/wiki/Q911187","display_name":"Page view","level":5,"score":0.42932868003845215},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.4159373342990875},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.29353123903274536},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/laweb.2003.1250280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/laweb.2003.1250280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/LEOS 3rd International Conference on Numerical Simulation of Semiconductor Optoelectronic Devices (IEEE Cat. No.03EX726)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.9275","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.9275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/research/sv/PageTurner/laweb.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.107","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.la-web.org/stamped/05_fetterly_d.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.5304","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.5304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/research/sv/PageTurner/laweb.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.883.4738","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.883.4738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.princeton.edu/courses/archive/spr05/cos598E/bib/fetterly03evolution.pdf","raw_type":"text"},{"id":"mag:318559539","is_oa":true,"landing_page_url":"http://research.microsoft.com/pubs/73807/laweb.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S114499935","display_name":"Journal of Web Engineering","issn_l":"1540-9589","issn":["1540-9589","1544-5976"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4366111290","host_organization_name":"River Publishers","host_organization_lineage":["https://openalex.org/P4366111290"],"host_organization_lineage_names":["River Publishers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Web Engineering","raw_type":null}],"best_oa_location":{"id":"mag:318559539","is_oa":true,"landing_page_url":"http://research.microsoft.com/pubs/73807/laweb.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S114499935","display_name":"Journal of Web Engineering","issn_l":"1540-9589","issn":["1540-9589","1544-5976"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4366111290","host_organization_name":"River Publishers","host_organization_lineage":["https://openalex.org/P4366111290"],"host_organization_lineage_names":["River Publishers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Web Engineering","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1609518033","https://openalex.org/W1614703486","https://openalex.org/W1969148345","https://openalex.org/W1987777228","https://openalex.org/W1997438973","https://openalex.org/W2081193615","https://openalex.org/W2087303323","https://openalex.org/W2123845384","https://openalex.org/W2139532006","https://openalex.org/W2140279085","https://openalex.org/W2152565070","https://openalex.org/W2169189540","https://openalex.org/W2169557227","https://openalex.org/W4250366158","https://openalex.org/W6636190696","https://openalex.org/W6680536191"],"related_works":["https://openalex.org/W2139532006","https://openalex.org/W2152565070","https://openalex.org/W2085922539","https://openalex.org/W2159448973","https://openalex.org/W182781187","https://openalex.org/W2181479107","https://openalex.org/W2400786132","https://openalex.org/W2295656603","https://openalex.org/W2394675604","https://openalex.org/W651408065","https://openalex.org/W1898993154","https://openalex.org/W2012833704","https://openalex.org/W1533275392","https://openalex.org/W2120136770","https://openalex.org/W1971772794","https://openalex.org/W2026739782","https://openalex.org/W2099495525","https://openalex.org/W3093736937","https://openalex.org/W2084432930","https://openalex.org/W1534396019"],"abstract_inverted_index":{"We":[0,19,38,60,83],"expand":[1],"on":[2,14,28],"a":[3,21,29],"1997":[4],"study":[5],"of":[6,11,23,35,42,47,54,64,88,99,115,137,158,169],"the":[7,15,33,146,166,170],"amount":[8],"and":[9,50,74,149],"distribution":[10],"near-duplicate":[12,55,89],"pages":[13,27,44,67,129],"World":[16],"Wide":[17],"Web.":[18],"downloaded":[20],"set":[22],"150":[24],"million":[25],"Web":[26,66,121],"weekly":[30],"basis":[31],"over":[32,58],"span":[34],"11":[36],"weeks.":[37],"then":[39],"determined":[40],"which":[41],"these":[43],"are":[45,68,77,91,97,102],"near-duplicates":[46,98,108,136],"one":[48,100,138,156],"another,":[49],"tracked":[51],"how":[52],"clusters":[53,87],"documents":[56,90,95],"evolved":[57],"time.":[59],"found":[61,85,133],"that":[62,75,86,96,127,130,159,178],"29.2%":[63],"all":[65],"very":[69,103],"similar":[70],"to":[71,80,105,118,134,142,153,164,182],"other":[72,81,171],"pages,":[73],"22.2%":[76],"virtually":[78],"identical":[79],"pages.":[82],"also":[84],"fairly":[92,125],"stable:":[93],"Two":[94],"another":[101,139],"likely":[104],"still":[106],"be":[107,124,135,143,180],"10":[109],"weeks":[110],"later.":[111],"This":[112],"result":[113],"is":[114],"significant":[116],"relevance":[117],"search":[119],"engines:":[120],"crawlers":[122],"can":[123,179],"confident":[126],"two":[128],"have":[131],"been":[132],"will":[140],"continue":[141],"so":[144],"for":[145],"foreseeable":[147],"future,":[148],"may":[150],"thus":[151],"decide":[152],"recrawl":[154],"only":[155],"version":[157],"page,":[160],"or":[161],"at":[162],"least":[163],"lower":[165],"download":[167],"priority":[168],"versions,":[172],"thereby":[173],"freeing":[174],"up":[175],"crawling":[176],"resources":[177],"brought":[181],"bear":[183],"more":[184],"productively":[185],"somewhere":[186],"else.":[187]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
