{"id":"https://openalex.org/W2159869159","doi":"https://doi.org/10.1145/1526709.1526842","title":"Sitemaps","display_name":"Sitemaps","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W2159869159","doi":"https://doi.org/10.1145/1526709.1526842","mag":"2159869159"},"language":"en","primary_location":{"id":"doi:10.1145/1526709.1526842","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","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/A5052102699","display_name":"Uri Schonfeld","orcid":null},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"funder","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Uri Schonfeld","raw_affiliation_strings":["UCLA Computer Science Department, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"UCLA Computer Science Department, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048031963","display_name":"Narayanan Shivakumar","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narayanan Shivakumar","raw_affiliation_strings":["Google Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052102699"],"corresponding_institution_ids":["https://openalex.org/I2799798094"],"apc_list":null,"apc_paid":null,"fwci":7.403,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.97181487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"991","last_page":"1000"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9704999923706055,"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":0.9699000120162964,"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/web-crawler","display_name":"Web crawler","score":0.8301356434822083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7945743203163147},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7338979244232178},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.664988100528717},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6163622736930847},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6051636934280396},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5936331748962402},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5824165940284729},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.566230297088623},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.5272803902626038},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4562039375305176},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.3447762131690979},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08866807818412781}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8301356434822083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945743203163147},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7338979244232178},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.664988100528717},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6163622736930847},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6051636934280396},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5936331748962402},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5824165940284729},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.566230297088623},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.5272803902626038},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4562039375305176},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.3447762131690979},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08866807818412781},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1526709.1526842","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W14315322","https://openalex.org/W1566984846","https://openalex.org/W1987272746","https://openalex.org/W1987365175","https://openalex.org/W2007687650","https://openalex.org/W2014126717","https://openalex.org/W2030453570","https://openalex.org/W2038378248","https://openalex.org/W2053049304","https://openalex.org/W2066636486","https://openalex.org/W2094930182","https://openalex.org/W2097704339","https://openalex.org/W2105533042","https://openalex.org/W2112104357","https://openalex.org/W2113184419","https://openalex.org/W2125969310","https://openalex.org/W2127536142","https://openalex.org/W2128941908","https://openalex.org/W2145349611","https://openalex.org/W2145990704","https://openalex.org/W2148738951","https://openalex.org/W2151932833","https://openalex.org/W2157748587","https://openalex.org/W2159869159","https://openalex.org/W2293888960","https://openalex.org/W4241558715"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2095543197","https://openalex.org/W2371838993","https://openalex.org/W1770021664","https://openalex.org/W2980544443","https://openalex.org/W2070988406"],"abstract_inverted_index":{"Comprehensive":[0],"coverage":[1,124],"of":[2,33,53,111,136],"the":[3,26,31,37,48,51],"public":[4],"web":[5,9,40,66,69,77],"is":[6,41,74],"crucial":[7],"to":[8,16,43,85,100],"search":[10,83,90,101],"engines.":[11,102],"Search":[12],"engines":[13,84,91],"use":[14],"crawlers":[15],"retrieve":[17],"pages":[18,34],"and":[19,60,68,89,125,145,153],"then":[20],"discover":[21],"new":[22],"ones":[23],"by":[24,81,96],"extracting":[25],"pages'":[27],"outgoing":[28],"links.":[29],"However,":[30],"set":[32,52],"reachable":[35],"from":[36],"publicly":[38],"linked":[39],"estimated":[42],"be":[44,63],"significantly":[45],"smaller":[46],"than":[47],"invisible":[49],"web,":[50],"documents":[54],"that":[55,143],"have":[56],"no":[57],"incoming":[58],"links":[59],"can":[61],"only":[62],"retrieved":[64],"through":[65],"applications":[67],"forms.":[70],"The":[71],"Sitemaps":[72,144],"protocol":[73,78],"a":[75,108],"fast-growing":[76],"supported":[79],"jointly":[80],"major":[82],"help":[86],"content":[87],"creators":[88],"unlock":[92],"this":[93,104],"hidden":[94],"data":[95],"making":[97],"it":[98],"available":[99],"In":[103],"paper,":[105],"we":[106],"perform":[107],"detailed":[109],"study":[110],"how":[112],"\"classic\"":[113],"discovery":[114,146],"crawling":[115,147],"compares":[116],"with":[117],"Sitemaps,":[118],"in":[119],"key":[120,128],"measures":[121],"such":[122],"as":[123,131,133],"freshness":[126],"over":[127,134],"representative":[129],"websites":[130],"well":[132],"billions":[135],"URLs":[137],"seen":[138],"at":[139],"Google.":[140],"We":[141],"observe":[142],"complement":[148],"each":[149],"other":[150],"very":[151],"well,":[152],"offer":[154],"different":[155],"tradeoffs.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
