{"id":"https://openalex.org/W1968155810","doi":"https://doi.org/10.1145/775152.775247","title":"Efficient URL caching for world wide web crawling","display_name":"Efficient URL caching for world wide web crawling","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1968155810","doi":"https://doi.org/10.1145/775152.775247","mag":"1968155810"},"language":"en","primary_location":{"id":"doi:10.1145/775152.775247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775152.775247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twelfth international conference on World Wide Web  - WWW '03","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/A5108541542","display_name":"Andrei Broder","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrei Z. Broder","raw_affiliation_strings":["IBM TJ Watson Research Center, Hawthorne, NY","IBM TJ. Watson Res. Center, Hawthorne, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center, Hawthorne, NY","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM TJ. Watson Res. Center, Hawthorne, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","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":"Marc Najork","raw_affiliation_strings":["Microsoft Research, Mountain View, CA","[Microsoft Research, Mountain View, CA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, CA","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/A5113681033","display_name":"Janet L. Wiener","orcid":null},"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":"Janet L. Wiener","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.4091,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.97693792,"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":"679","last_page":"679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9894999861717224,"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":0.8306789398193359},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8042181730270386},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6646782755851746},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5007727146148682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306789398193359},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8042181730270386},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6646782755851746},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5007727146148682},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/775152.775247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775152.775247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twelfth international conference on World Wide Web  - WWW '03","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.8360","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.8360","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/sv-pubs/p96-broder/p96-broder.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.1884","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.1884","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/sv-pubs/p96-broder/p96-broder.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":34,"referenced_works":["https://openalex.org/W58642631","https://openalex.org/W70368499","https://openalex.org/W100509257","https://openalex.org/W625975574","https://openalex.org/W1493892051","https://openalex.org/W1538592187","https://openalex.org/W1551265161","https://openalex.org/W1552828154","https://openalex.org/W1566984846","https://openalex.org/W1585070348","https://openalex.org/W1603416030","https://openalex.org/W1605217017","https://openalex.org/W1613836731","https://openalex.org/W1614703486","https://openalex.org/W1659541576","https://openalex.org/W1709754610","https://openalex.org/W1965375374","https://openalex.org/W1987225815","https://openalex.org/W2000273502","https://openalex.org/W2006524576","https://openalex.org/W2007687650","https://openalex.org/W2018928332","https://openalex.org/W2029341294","https://openalex.org/W2039100193","https://openalex.org/W2066636486","https://openalex.org/W2080745194","https://openalex.org/W2140279085","https://openalex.org/W2147164982","https://openalex.org/W2161088492","https://openalex.org/W2164542999","https://openalex.org/W2169557227","https://openalex.org/W2175110005","https://openalex.org/W2295141584","https://openalex.org/W3198160809"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2152505903"],"abstract_inverted_index":{"Crawling":[0],"the":[1,6,25,33,36,85,100,132,140,156],"web":[2,37,174,218],"is":[3,9,142,165,229,232,266],"deceptively":[4],"simple:":[5],"basic":[7],"algorithm":[8],"(a)":[10,88],"Fetch":[11],"a":[12,58,63,78,93,115,126,152,214,239,247,259,262,271],"page":[13],"(b)":[14],"Parse":[15],"it":[16],"to":[17,62,119,137,143,147,166,287],"extract":[18],"all":[19,24],"linked":[20],"URLs":[21,26],"(c)":[22,103],"For":[23],"not":[27],"seen":[28],"before,":[29],"repeat":[30],"(a)-(c).":[31],"However,":[32],"size":[34,256],"of":[35,47,84,155,162,241,250],"(estimated":[38,49],"at":[39,50,258],"over":[40,108,222],"4":[41],"billion":[42,224],"pages)":[43],"and":[44,66,81,98,186,188,193,290],"its":[45],"rate":[46,249],"change":[48],"7%":[51],"per":[52,96,112],"week)":[53],"move":[54],"this":[55,163,254,295],"plan":[56],"from":[57,213],"trivial":[59],"programming":[60],"exercise":[61],"serious":[64],"algorithmic":[65],"system":[67],"design":[68],"challenge.":[69],"Indeed,":[70],"these":[71,202],"two":[72],"factors":[73],"alone":[74],"imply":[75],"that":[76,145,220,230,281],"for":[77,173,294],"reasonably":[79],"fresh":[80],"complete":[82],"crawl":[83,219],"web,":[86],"step":[87],"must":[89,104],"be":[90,105],"executed":[91],"about":[92,198],"thousand":[94,110],"times":[95,111],"second,":[97],"thus":[99],"membership":[101,133],"test":[102,141],"done":[106],"well":[107],"ten":[109],"second":[113],"against":[114],"set":[116],"too":[117],"large":[118],"store":[120,148],"in":[121,149,236],"main":[122,150,160,227],"memory.":[123],"This":[124],"requires":[125],"distributed":[127],"architecture,":[128],"which":[129],"further":[130],"complicates":[131],"test.A":[134],"crucial":[135],"way":[136],"speed":[138],"up":[139],"cache,":[144,184],"is,":[146],"memory":[151],"(dynamic)":[153],"subset":[154],"\"seen\"":[157],"URLs.":[158],"The":[159],"goal":[161],"paper":[164],"carefully":[167],"investigate":[168],"several":[169],"URL":[170],"caching":[171,192,231],"techniques":[172],"crawling.":[175],"We":[176,196,279],"consider":[177],"both":[178],"practical":[179],"algorithms:":[180],"random":[181],"replacement,":[182],"static":[183],"LRU,":[185],"CLOCK,":[187],"theoretical":[189],"limits:":[190],"clairvoyant":[191],"infinite":[194],"cache.":[195],"performed":[197],"1,800":[199],"simulations":[200],"using":[201,208],"algorithms":[203],"with":[204],"various":[205],"cache":[206,240,255,265,274],"sizes,":[207],"actual":[209],"log":[210],"data":[211],"extracted":[212],"massive":[215],"33":[216],"day":[217],"issued":[221],"one":[223],"HTTP":[225],"requests.Our":[226],"conclusion":[228],"very":[233],"effective":[234,269],"-":[235],"our":[237,288],"setup,":[238],"roughly":[242],"50,000":[243],"entries":[244],"can":[245],"achieve":[246],"hit":[248],"almost":[251],"80%.":[252],"Interestingly,":[253],"falls":[257],"critical":[260,283],"point:":[261],"substantially":[263,272],"smaller":[264],"much":[267],"less":[268],"while":[270],"larger":[273],"brings":[275],"little":[276],"additional":[277],"benefit.":[278],"conjecture":[280],"such":[282],"points":[284],"are":[285],"inherent":[286],"problem":[289],"venture":[291],"an":[292],"explanation":[293],"phenomenon.":[296]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}