{"id":"https://openalex.org/W1976186411","doi":"https://doi.org/10.1145/1480506.1480512","title":"Compressed collections for simulated crawling","display_name":"Compressed collections for simulated crawling","publication_year":2008,"publication_date":"2008-11-30","ids":{"openalex":"https://openalex.org/W1976186411","doi":"https://doi.org/10.1145/1480506.1480512","mag":"1976186411"},"language":"en","primary_location":{"id":"doi:10.1145/1480506.1480512","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1480506.1480512","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"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":"ACM SIGIR Forum","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/A5001389367","display_name":"Alessio Orlandi","orcid":"https://orcid.org/0000-0002-0676-8796"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Orlandi","raw_affiliation_strings":["Universit\u00e0 di Pisa, Italy","Universita di Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Universita di Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027824085","display_name":"Sebastiano Vigna","orcid":"https://orcid.org/0000-0002-3257-651X"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sebastiano Vigna","raw_affiliation_strings":["Universit\u00e0 degli Studi di Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 degli Studi di Milano, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.1037826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"42","issue":"2","first_page":"39","last_page":"44"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9925000071525574,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9879999756813049,"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":0.9124265313148499},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.833023726940155},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.6627357006072998},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6233578324317932},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5809409618377686},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48509061336517334},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.45076924562454224},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4216769337654114},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3426671326160431},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2271479070186615},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15203508734703064},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09393754601478577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9124265313148499},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.833023726940155},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.6627357006072998},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6233578324317932},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5809409618377686},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48509061336517334},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.45076924562454224},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4216769337654114},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3426671326160431},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2271479070186615},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15203508734703064},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09393754601478577},{"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":3,"locations":[{"id":"doi:10.1145/1480506.1480512","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1480506.1480512","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"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":"ACM SIGIR Forum","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.147.3517","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.3517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vigna.dsi.unimi.it/ftp/papers/CompressedCollections.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.512","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sigir.org/forum/2008D/papers/2008d_sigirforum_orlandi.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W17958277","https://openalex.org/W1489022643","https://openalex.org/W1489992655","https://openalex.org/W1994727615","https://openalex.org/W2000273502","https://openalex.org/W2043770080","https://openalex.org/W2057223122","https://openalex.org/W2073562093","https://openalex.org/W2153987307"],"related_works":["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/W2089702591","https://openalex.org/W4255854114"],"abstract_inverted_index":{"Collections":[0],"are":[1],"a":[2,14,29,33,87,91,105],"fundamental":[3],"tool":[4],"for":[5,17],"reproducible":[6],"evaluation":[7],"of":[8,28,46,49,93,96,109],"information":[9],"retrieval":[10],"techniques.":[11,111],"We":[12,85],"describe":[13,86],"new":[15],"method":[16],"distributing":[18],"the":[19,47,57,76,80,97],"document":[20],"lengths":[21],"and":[22,36],"term":[23],"counts":[24],"(a.k.a.":[25],"within-document":[26],"frequencies)":[27],"web":[30,59],"snapshot":[31],"in":[32,102],"highly":[34],"compressed":[35,61],"nonetheless":[37],"quickly":[38],"accessible":[39],"form.":[40],"Our":[41],"main":[42],"application":[43],"is":[44],"reproducibility":[45],"behaviour":[48],"focused":[50],"crawlers:":[51],"by":[52],"coupling":[53],"our":[54,110],"collection":[55,88],"with":[56,62,104],"corresponding":[58],"graph":[60],"WebGraph":[63],"[3]":[64],"we":[65],"make":[66],"it":[67],"possible":[68],"to":[69,75],"apply":[70],"text-based":[71],"machine":[72],"learning":[73],"tools":[74],"collection,":[77],"while":[78],"keeping":[79],"data":[81],"set":[82],"footprint":[83],"small.":[84],"based":[89],"on":[90],"crawl":[92],"100":[94],"Mpages":[95],".uk":[98],"domain,":[99],"publicly":[100],"available":[101],"bundle":[103],"Java":[106],"open-source":[107],"implementation":[108]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
