{"id":"https://openalex.org/W2085922539","doi":"https://doi.org/10.1145/1148170.1148222","title":"Finding near-duplicate web pages","display_name":"Finding near-duplicate web pages","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2085922539","doi":"https://doi.org/10.1145/1148170.1148222","mag":"2085922539"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/99373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003641345","display_name":"Monika Henzinger","orcid":"https://orcid.org/0000-0002-5008-6530"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH","US"],"is_corresponding":true,"raw_author_name":"Monika Henzinger","raw_affiliation_strings":["Google Inc. &amp; Ecole F\u00e9d\u00e9rale de Lausanne (EPFL)"],"affiliations":[{"raw_affiliation_string":"Google Inc. &amp; Ecole F\u00e9d\u00e9rale de Lausanne (EPFL)","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5003641345"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":19.6028,"has_fulltext":true,"cited_by_count":432,"citation_normalized_percentile":{"value":0.99581751,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"284","last_page":"291"},"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":0.998199999332428,"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":0.998199999332428,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9947999715805054,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.7628085613250732},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6519556045532227},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.6188782453536987},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6085447669029236},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5165752172470093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49285387992858887},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45178350806236267},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.42942142486572266},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.4204729497432709},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36725810170173645},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.2777145504951477},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.26870936155319214},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.23433566093444824},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2018313705921173},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.1568681299686432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628085613250732},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6519556045532227},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.6188782453536987},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6085447669029236},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5165752172470093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49285387992858887},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45178350806236267},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.42942142486572266},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.4204729497432709},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36725810170173645},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.2777145504951477},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26870936155319214},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.23433566093444824},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2018313705921173},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.1568681299686432},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1148170.1148222","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:99373","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/99373","pdf_url":"http://infoscience.epfl.ch/record/99373","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"http://infoscience.epfl.ch/record/99373","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:99373","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/99373","pdf_url":"http://infoscience.epfl.ch/record/99373","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"http://infoscience.epfl.ch/record/99373","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2085922539.pdf","grobid_xml":"https://content.openalex.org/works/W2085922539.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1536700701","https://openalex.org/W1596691921","https://openalex.org/W1609518033","https://openalex.org/W1614703486","https://openalex.org/W1941707302","https://openalex.org/W1997657677","https://openalex.org/W2007842132","https://openalex.org/W2012833704","https://openalex.org/W2128272588","https://openalex.org/W2139532006","https://openalex.org/W2152565070","https://openalex.org/W2164634022","https://openalex.org/W2173213060","https://openalex.org/W6611141452","https://openalex.org/W6636190696","https://openalex.org/W6640489131","https://openalex.org/W6682678078"],"related_works":["https://openalex.org/W1881353113","https://openalex.org/W2387616437","https://openalex.org/W1556894713","https://openalex.org/W2187771236","https://openalex.org/W2008577673","https://openalex.org/W2104034683","https://openalex.org/W2054902748","https://openalex.org/W2127067408","https://openalex.org/W1607291588","https://openalex.org/W2997495867"],"abstract_inverted_index":{"Broder":[0,104],"et":[1,105],"al.'s":[2,106],"[3]":[3],"shingling":[4],"algorithm":[5,85,112],"and":[6],"Charikar's":[7,84],"[4]":[8],"random":[9],"projection":[10],"based":[11],"approach":[12],"are":[13],"considered":[14],"\"state-of-the-art\"":[15],"algorithms":[16,23,39,61],"for":[17,64,77,103],"finding":[18,65],"near-duplicate":[19,66,78,88],"web":[20,32,52],"pages.":[21,53],"Both":[22],"were":[24],"either":[25],"developed":[26],"at":[27],"or":[28],"used":[29],"by":[30],"popular":[31],"search":[33],"engines.":[34],"We":[35,108],"compare":[36],"the":[37,60,69,120,123],"two":[38],"on":[40,46,68,80,90],"a":[41,47,95,110],"very":[42],"large":[43],"scale,":[44],"namely":[45,99],"set":[48],"of":[49,59,119,122],"1.6B":[50],"distinct":[51],"The":[54],"results":[55],"show":[56],"that":[57],"neither":[58],"works":[62],"well":[63],"pairs":[67,79,89],"same":[70],"site,":[71],"while":[72],"both":[73],"achieve":[74],"high":[75],"precision":[76,97,115],"different":[81,91],"sites.":[82],"Since":[83],"finds":[86],"more":[87],"sites,":[92],"it":[93],"achieves":[94,114],"better":[96],"overall,":[98],"0.50":[100],"versus":[101],"0.38":[102],"algorithm.":[107],"present":[109],"combined":[111],"which":[113],"0.79":[116],"with":[117],"79%":[118],"recall":[121],"other":[124],"algorithms.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":36},{"year":2014,"cited_by_count":50},{"year":2013,"cited_by_count":35},{"year":2012,"cited_by_count":27}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2016-06-24T00:00:00"}
