{"id":"https://openalex.org/W2884612586","doi":"https://doi.org/10.1073/pnas.1801519115","title":"Tractable near-optimal policies for crawling","display_name":"Tractable near-optimal policies for crawling","publication_year":2018,"publication_date":"2018-07-23","ids":{"openalex":"https://openalex.org/W2884612586","doi":"https://doi.org/10.1073/pnas.1801519115","mag":"2884612586","pmid":"https://pubmed.ncbi.nlm.nih.gov/30038026"},"language":"en","primary_location":{"id":"doi:10.1073/pnas.1801519115","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1801519115","pdf_url":"https://www.pnas.org/content/pnas/115/32/8099.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.pnas.org/content/pnas/115/32/8099.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082061504","display_name":"Yossi Azar","orcid":"https://orcid.org/0000-0002-5097-8993"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yossi Azar","raw_affiliation_strings":["Department of Computer Science, Tel-Aviv University, Tel-Aviv 69978, Israel;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tel-Aviv University, Tel-Aviv 69978, Israel;","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043228682","display_name":"Eric Horvitz","orcid":"https://orcid.org/0000-0002-8823-0614"},"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":"Eric Horvitz","raw_affiliation_strings":["Microsoft Research, Redmond, WA 98052;"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052;","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047720470","display_name":"Eyal Lubetzky","orcid":"https://orcid.org/0000-0002-2281-3542"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eyal Lubetzky","raw_affiliation_strings":["Courant Institute of Mathematical Sciences, New York University, New York, NY 10012;"],"affiliations":[{"raw_affiliation_string":"Courant Institute of Mathematical Sciences, New York University, New York, NY 10012;","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020836845","display_name":"Yuval Peres","orcid":"https://orcid.org/0000-0001-5456-6323"},"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":"Yuval Peres","raw_affiliation_strings":["Microsoft Research, Redmond, WA 98052;"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052;","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009660759","display_name":"Dafna Shahaf","orcid":"https://orcid.org/0000-0003-3261-0818"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dafna Shahaf","raw_affiliation_strings":["School of Computer Science, Hebrew University, Jerusalem 91904, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hebrew University, Jerusalem 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082061504"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":3.322,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92842467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"115","issue":"32","first_page":"8099","last_page":"8103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","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"}},"topics":[{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","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/T11478","display_name":"Caching and Content Delivery","score":0.9980999827384949,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.995199978351593,"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/computer-science","display_name":"Computer science","score":0.8236949443817139},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7744449377059937},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6259328126907349},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.600433886051178},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5889410972595215},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.48778706789016724},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4779244065284729},{"id":"https://openalex.org/keywords/randomized-algorithm","display_name":"Randomized algorithm","score":0.4380866587162018},{"id":"https://openalex.org/keywords/dynamic-web-page","display_name":"Dynamic web page","score":0.42750874161720276},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3442051112651825},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3329128921031952},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24418854713439941},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21021446585655212},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.11638841032981873},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11560219526290894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8236949443817139},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7744449377059937},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6259328126907349},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.600433886051178},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5889410972595215},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.48778706789016724},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4779244065284729},{"id":"https://openalex.org/C128669082","wikidata":"https://www.wikidata.org/wiki/Q583461","display_name":"Randomized algorithm","level":2,"score":0.4380866587162018},{"id":"https://openalex.org/C100158260","wikidata":"https://www.wikidata.org/wiki/Q1650567","display_name":"Dynamic web page","level":3,"score":0.42750874161720276},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3442051112651825},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3329128921031952},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24418854713439941},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21021446585655212},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.11638841032981873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11560219526290894},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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},{"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":4,"locations":[{"id":"doi:10.1073/pnas.1801519115","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1801519115","pdf_url":"https://www.pnas.org/content/pnas/115/32/8099.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},{"id":"pmid:30038026","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30038026","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences of the United States of America","raw_type":null},{"id":"pmh:oai:europepmc.org:5043484","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6094111","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6094111","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6094111","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Natl Acad Sci U S A","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1073/pnas.1801519115","is_oa":true,"landing_page_url":"https://doi.org/10.1073/pnas.1801519115","pdf_url":"https://www.pnas.org/content/pnas/115/32/8099.full.pdf","source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2884612586.pdf","grobid_xml":"https://content.openalex.org/works/W2884612586.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W75161650","https://openalex.org/W75581828","https://openalex.org/W1519369768","https://openalex.org/W1964285561","https://openalex.org/W1976624301","https://openalex.org/W1987272746","https://openalex.org/W2016122268","https://openalex.org/W2020858128","https://openalex.org/W2038378248","https://openalex.org/W2050880818","https://openalex.org/W2090925153","https://openalex.org/W2096318933","https://openalex.org/W2109488193","https://openalex.org/W2112053513","https://openalex.org/W2137849194","https://openalex.org/W2138310207","https://openalex.org/W2142211218","https://openalex.org/W2911840101","https://openalex.org/W4253041633"],"related_works":["https://openalex.org/W81688156","https://openalex.org/W2566024741","https://openalex.org/W2392690423","https://openalex.org/W2366646628","https://openalex.org/W2015408864","https://openalex.org/W2540597016","https://openalex.org/W2108008503","https://openalex.org/W1995641595","https://openalex.org/W1781390351","https://openalex.org/W4285383156"],"abstract_inverted_index":{"The":[0,36],"problem":[1],"of":[2,7,50,81,127],"maintaining":[3],"a":[4,41,115,119],"local":[5],"cache":[6],"n":[8],"constantly":[9],"changing":[10],"pages":[11,29,52],"arises":[12],"in":[13,86,100,112,123],"multiple":[14],"mechanisms":[15],"such":[16],"as":[17,69],"web":[18],"crawlers":[19],"and":[20,43,59],"proxy":[21],"servers.":[22],"In":[23],"these,":[24],"the":[25,48,92,107,128],"resources":[26],"for":[27,30,78],"polling":[28,42],"possible":[31],"updates":[32],"are":[33,54],"typically":[34],"limited.":[35],"goal":[37],"is":[38],"to":[39,56,110],"devise":[40],"fetching":[44],"policy":[45,95,121],"that":[46,53,91,122],"maximizes":[47],"utility":[49],"served":[51],"up":[55],"date.":[57],"Cho":[58],"Garcia-Molina":[60],"[(2003)":[61],"<i>ACM":[62],"Trans":[63],"Database":[64],"Syst</i>":[65],"28:390-426]":[66],"formulated":[67],"this":[68],"an":[70],"optimization":[71],"problem,":[72],"which":[73],"can":[74,96],"be":[75,97],"solved":[76],"numerically":[77],"small":[79],"values":[80],"n,":[82],"but":[83],"appears":[84],"intractable":[85],"general.":[87],"Here,":[88],"we":[89],"show":[90],"optimal":[93,108],"randomized":[94],"found":[98],"exactly":[99],"[Formula:":[101],"see":[102],"text]":[103],"operations.":[104],"Moreover,":[105],"using":[106],"probabilities":[109],"define":[111],"linear":[113],"time":[114],"deterministic":[116],"schedule":[117],"yields":[118],"tractable":[120],"experiments":[124],"attains":[125],"99%":[126],"optimum.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
