{"id":"https://openalex.org/W2135402295","doi":"https://doi.org/10.14778/1687627.1687694","title":"SHARC","display_name":"SHARC","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2135402295","doi":"https://doi.org/10.14778/1687627.1687694","mag":"2135402295"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687694","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687694","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5045865871","display_name":"Dimitar Denev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dimitar Denev","raw_affiliation_strings":["Max Planck Institute for Informatics Campus, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105524725","display_name":"Art\u016bras Ma\u017eeika","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arturas Mazeika","raw_affiliation_strings":["Max Planck Institute for Informatics Campus, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003469648","display_name":"Marc Spaniol","orcid":"https://orcid.org/0000-0002-5094-4523"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Spaniol","raw_affiliation_strings":["Max Planck Institute for Informatics Campus, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088135366","display_name":"Gerhard Weikum","orcid":"https://orcid.org/0000-0003-4959-6098"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Weikum","raw_affiliation_strings":["Max Planck Institute for Informatics Campus, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045865871"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":5.1821,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95828207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"586","last_page":"597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9958999752998352,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9878000020980835,"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":0.766654372215271},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7081613540649414},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7017581462860107},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5084902048110962},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5001969337463379},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4960192143917084},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4729433059692383},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.4246007204055786},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.41683071851730347},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.41475069522857666},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3757612705230713},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2755430340766907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766654372215271},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7081613540649414},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7017581462860107},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5084902048110962},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5001969337463379},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4960192143917084},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4729433059692383},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.4246007204055786},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.41683071851730347},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.41475069522857666},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3757612705230713},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2755430340766907},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1687627.1687694","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687694","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1492633670","https://openalex.org/W1593043209","https://openalex.org/W1674850363","https://openalex.org/W1976624301","https://openalex.org/W1979809502","https://openalex.org/W1987272746","https://openalex.org/W1990129631","https://openalex.org/W2007687650","https://openalex.org/W2029341294","https://openalex.org/W2050347474","https://openalex.org/W2097704339","https://openalex.org/W2099126271","https://openalex.org/W2110073539","https://openalex.org/W2126122940","https://openalex.org/W2127536142","https://openalex.org/W2135252439","https://openalex.org/W2145990704","https://openalex.org/W2148931201","https://openalex.org/W2157748587","https://openalex.org/W2165862792","https://openalex.org/W3091121169","https://openalex.org/W3204318296","https://openalex.org/W4210438348","https://openalex.org/W4249960090","https://openalex.org/W6657826343","https://openalex.org/W7044087731"],"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/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W4255854114","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Web":[0,40,55,71,109,154],"archives":[1,72],"preserve":[2],"the":[3,43,62,67,132,143],"history":[4],"of":[5,38,95,108],"born-digital":[6],"content":[7],"and":[8,16,22,46,73,91,121,165,194,206],"offer":[9],"great":[10],"potential":[11],"for":[12,29,65,74,99,131,166,211],"sociologists,":[13],"business":[14],"analysts,":[15],"legal":[17],"experts":[18],"on":[19,116,152],"intellectual":[20],"property":[21],"compliance":[23],"issues.":[24],"Data":[25],"quality":[26,69,80,86],"is":[27,103,158],"crucial":[28],"these":[30],"purposes.":[31],"Ideally,":[32],"crawlers":[33],"should":[34],"gather":[35],"sharp":[36],"captures":[37],"entire":[39],"sites,":[41],"but":[42],"politeness":[44],"etiquette":[45],"completeness":[47],"requirement":[48],"mandate":[49],"very":[50],"slow,":[51],"long-duration":[52],"crawling":[53],"while":[54,156],"sites":[56,205],"undergo":[57],"changes.":[58],"This":[59],"paper":[60],"presents":[61],"SHARC":[63],"framework":[64],"assessing":[66,167],"data":[68],"in":[70,181,191],"tuning":[75],"capturing":[76],"strategies":[77,98,173,187],"towards":[78],"better":[79],"with":[81,201],"given":[82],"resources.":[83],"We":[84,124,141],"define":[85],"measures,":[87],"characterize":[88],"their":[89,178],"properties,":[90],"derive":[92],"a":[93,126,153,162,182,192,207,212],"suite":[94],"quality-conscious":[96],"scheduling":[97],"archive":[100],"crawling.":[101],"It":[102],"assumed":[104],"that":[105,149,174],"change":[106,137],"rates":[107,138],"pages":[110,176],"can":[111],"be":[112,197],"statistically":[113],"predicted":[114],"based":[115],"page":[117],"types,":[118],"directory":[119],"depths,":[120],"URL":[122],"names.":[123],"develop":[125],"stochastically":[127],"optimal":[128],"crawl":[129,209],"algorithm":[130,148],"offline":[133],"case":[134],"where":[135],"all":[136],"are":[139,188],"known.":[140],"generalize":[142],"approach":[144],"into":[145],"an":[146],"online":[147],"detect":[150],"information":[151],"site":[155,163],"it":[157],"crawled.":[159],"For":[160],"dating":[161],"capture":[164],"its":[168],"quality,":[169],"we":[170],"propose":[171],"several":[172],"revisit":[175],"after":[177],"initial":[179],"downloads":[180],"judiciously":[183],"chosen":[184],"order.":[185],"All":[186],"fully":[189],"implemented":[190],"testbed,":[193],"shown":[195],"to":[196],"effective":[198],"by":[199],"experiments":[200],"both":[202],"synthetically":[203],"generated":[204],"daily":[208],"series":[210],"medium-sized":[213],"site.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
