{"id":"https://openalex.org/W4281653454","doi":"https://doi.org/10.1145/3529372.3530934","title":"Investigating bloom filters for web archives' holdings","display_name":"Investigating bloom filters for web archives' holdings","publication_year":2022,"publication_date":"2022-06-06","ids":{"openalex":"https://openalex.org/W4281653454","doi":"https://doi.org/10.1145/3529372.3530934"},"language":"en","primary_location":{"id":"doi:10.1145/3529372.3530934","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529372.3530934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073828706","display_name":"Martin Klein","orcid":"https://orcid.org/0000-0003-0130-2097"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Klein","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027991610","display_name":"Lyudmila Balakireva","orcid":"https://orcid.org/0000-0002-3919-3634"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lyudmila Balakireva","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063575387","display_name":"K Holub","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104481","display_name":"National and University Library in Zagreb","ror":"https://ror.org/01ereaj97","country_code":"HR","type":"archive","lineage":["https://openalex.org/I4210104481"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Karolina Holub","raw_affiliation_strings":["National and University Library in Zagreb, Zagreb, Croatia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and University Library in Zagreb, Zagreb, Croatia","institution_ids":["https://openalex.org/I4210104481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081560497","display_name":"Dra\u017eenko Celjak","orcid":"https://orcid.org/0000-0002-0585-3390"},"institutions":[{"id":"https://openalex.org/I181343428","display_name":"University of Zagreb","ror":"https://ror.org/00mv6sv71","country_code":"HR","type":"education","lineage":["https://openalex.org/I181343428"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Dra\u017eenko Celjak","raw_affiliation_strings":["University of Zagreb University, Zagreb, Croatia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zagreb University, Zagreb, Croatia","institution_ids":["https://openalex.org/I181343428"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073504602","display_name":"Ingeborg Rudomino","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104481","display_name":"National and University Library in Zagreb","ror":"https://ror.org/01ereaj97","country_code":"HR","type":"archive","lineage":["https://openalex.org/I4210104481"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Ingeborg Rudomino","raw_affiliation_strings":["National and University Library in Zagreb, Zagreb, Croatia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National and University Library in Zagreb, Zagreb, Croatia","institution_ids":["https://openalex.org/I4210104481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2696,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37006629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9965000152587891,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.991100013256073,"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/bloom-filter","display_name":"Bloom filter","score":0.9408482313156128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7872879505157471},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.764079213142395},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6776567697525024},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.6747465133666992},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5393097400665283},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.5323415398597717},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4554358422756195},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40140846371650696},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38521814346313477},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27546536922454834},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.11486777663230896},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.091071218252182}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.9408482313156128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872879505157471},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.764079213142395},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6776567697525024},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.6747465133666992},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5393097400665283},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.5323415398597717},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4554358422756195},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40140846371650696},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38521814346313477},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27546536922454834},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.11486777663230896},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.091071218252182},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3529372.3530934","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3529372.3530934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1904820966","https://openalex.org/W1965185568","https://openalex.org/W1993284846","https://openalex.org/W1994948642","https://openalex.org/W2074633331","https://openalex.org/W2156660460","https://openalex.org/W2157004265","https://openalex.org/W2159869159","https://openalex.org/W2166310193","https://openalex.org/W2258370040","https://openalex.org/W2293827470","https://openalex.org/W2338903762","https://openalex.org/W2343043900","https://openalex.org/W2417822008","https://openalex.org/W2464674082","https://openalex.org/W2478097356","https://openalex.org/W2520832747","https://openalex.org/W2546414884","https://openalex.org/W2569177048","https://openalex.org/W2810191764","https://openalex.org/W2964277307","https://openalex.org/W2968015434","https://openalex.org/W2968859891","https://openalex.org/W3100737583","https://openalex.org/W3173746341","https://openalex.org/W4244197987","https://openalex.org/W4300782170"],"related_works":["https://openalex.org/W2086572746","https://openalex.org/W2368605798","https://openalex.org/W2604468458","https://openalex.org/W2157216338","https://openalex.org/W1662107788","https://openalex.org/W121740227","https://openalex.org/W2135966669","https://openalex.org/W2732769800","https://openalex.org/W315172248","https://openalex.org/W2610007503"],"abstract_inverted_index":{"What":[0],"web":[1,32,110],"archives":[2],"hold":[3],"is":[4],"often":[5],"opaque":[6],"to":[7,17,57,88,119],"the":[8,14,22],"public":[9],"and":[10,26,30,54,65,79,97,114,122],"even":[11],"experts":[12],"in":[13,102],"domain":[15],"struggle":[16],"provide":[18],"precise":[19],"assessments.":[20],"Given":[21],"increasing":[23],"need":[24],"for":[25,68,77,109],"use":[27,47,60,112],"of":[28,35,42],"crawled":[29],"archived":[31],"resources,":[33],"discovery":[34],"individual":[36],"records":[37],"as":[38,40],"well":[39],"sharing":[41],"entire":[43],"holdings":[44],"are":[45],"pressing":[46],"cases.":[48,61],"We":[49,62,105],"investigate":[50],"Bloom":[51],"Filters":[52],"(BFs)":[53],"their":[55,69,72,86,107],"applicability":[56],"address":[58],"these":[59],"experiment":[63],"with":[64,94],"analyze":[66],"parameters":[67],"creation,":[70],"measure":[71],"performance,":[73],"outline":[74],"an":[75],"approach":[76],"scalability,":[78],"describe":[80],"various":[81,103],"pilot":[82],"implementations":[83],"that":[84],"showcase":[85],"potential":[87],"meet":[89],"our":[90],"needs.":[91],"BFs":[92],"come":[93],"beneficial":[95],"characteristics":[96],"hence":[98],"have":[99],"enjoyed":[100],"popularity":[101],"domains.":[104],"highlight":[106],"suitability":[108],"archiving":[111],"cases":[113],"how":[115],"they":[116],"can":[117],"contribute":[118],"very":[120],"fast":[121],"accurate":[123],"search":[124],"services.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
