{"id":"https://openalex.org/W4409657401","doi":"https://doi.org/10.1145/3696410.3714692","title":"A Scalable Crawling Algorithm Utilizing Noisy Change-Indicating Signals","display_name":"A Scalable Crawling Algorithm Utilizing Noisy Change-Indicating Signals","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657401","doi":"https://doi.org/10.1145/3696410.3714692"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714692","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714692","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714692","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022323474","display_name":"Julian Zimmert","orcid":"https://orcid.org/0000-0001-6929-9053"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Julian Zimmert","raw_affiliation_strings":["Google Research, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6929-9053","affiliations":[{"raw_affiliation_string":"Google Research, Berlin, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047520070","display_name":"R\u00f3bert Busa\u2010Fekete","orcid":"https://orcid.org/0000-0002-3691-650X"},"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":"R\u00f3bert Busa-Fekete","raw_affiliation_strings":["Google Research, New York City, USA"],"raw_orcid":"https://orcid.org/0000-0002-3691-650X","affiliations":[{"raw_affiliation_string":"Google Research, New York City, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041609088","display_name":"Andr\u00e1s Gy\u00f6rgy","orcid":"https://orcid.org/0000-0003-0586-4337"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s Gy\u00f6rgy","raw_affiliation_strings":["Google DeepMind, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-0586-4337","affiliations":[{"raw_affiliation_string":"Google DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007474610","display_name":"Linhai Qiu","orcid":"https://orcid.org/0000-0002-0571-581X"},"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":"Linhai Qiu","raw_affiliation_strings":["Google, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0000-0002-0571-581X","affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105774746","display_name":"H. H. F. Choi","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":"Hyomin Choi","raw_affiliation_strings":["Google, Chigago, USA"],"raw_orcid":"https://orcid.org/0009-0009-4176-5118","affiliations":[{"raw_affiliation_string":"Google, Chigago, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tzu-Wei Sung","orcid":"https://orcid.org/0009-0006-8627-9760"},"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":"Tzu-Wei Sung","raw_affiliation_strings":["Google, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0009-0006-8627-9760","affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Shen","orcid":"https://orcid.org/0009-0006-8567-964X"},"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":"Hao Shen","raw_affiliation_strings":["Google, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0009-0006-8567-964X","affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sharmila Subramaniam","orcid":"https://orcid.org/0009-0006-7253-5137"},"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":"Sharmila Subramaniam","raw_affiliation_strings":["Google, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0009-0006-7253-5137","affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":null,"display_name":"Li Xiao","orcid":"https://orcid.org/0009-0003-7224-3079"},"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":"Li Xiao","raw_affiliation_strings":["Google, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0009-0003-7224-3079","affiliations":[{"raw_affiliation_string":"Google, Sunnyvale, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5022323474"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03490306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4875","last_page":"4888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9934999942779541,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9934999942779541,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9764999747276306,"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/crawling","display_name":"Crawling","score":0.9183534383773804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7509381771087646},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5932408571243286},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4093160331249237},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07344290614128113}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9183534383773804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509381771087646},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5932408571243286},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4093160331249237},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07344290614128113},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714692","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714692","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714692","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714692","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409657401.pdf","grobid_xml":"https://content.openalex.org/works/W4409657401.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1976624301","https://openalex.org/W2030453570","https://openalex.org/W2038378248","https://openalex.org/W2109488193","https://openalex.org/W2560674852","https://openalex.org/W2884612586","https://openalex.org/W2990138404","https://openalex.org/W2997842680"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4393220254","https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W2385015894","https://openalex.org/W2171573941"],"abstract_inverted_index":{"Web":[0],"refresh":[1],"crawling":[2,104,157],"is":[3,25,96,106,182],"the":[4,17,33,36,39,53,103,110,126,138,141,162,196,208,213,223],"problem":[5,73],"of":[6,10,71,84,137,140,225],"keeping":[7],"a":[8,23,28,130,155,189],"cache":[9],"web":[11,47,85,134,148,151,186],"pages":[12,135,187],"fresh,":[13],"that":[14,38],"is,":[15],"having":[16],"most":[18],"recent":[19],"copy":[20],"available":[21,31],"when":[22,212],"page":[24,48,149],"requested,":[26],"given":[27],"limited":[29],"bandwidth":[30,198,215],"to":[32,45,150,184,207],"crawler.":[34],"Under":[35],"assumption":[37],"change":[40,122],"and":[41,119,124,204],"request":[42],"events,":[43],"resp.,":[44],"each":[46],"follow":[49],"independent":[50],"Poisson":[51],"processes,":[52],"optimal":[54,168,210],"scheduling":[55],"policy":[56,105],"was":[57],"derived":[58],"by":[59],"Azar":[60],"et":[61],"al.":[62],"2018.":[63],"In":[64],"this":[65,72],"paper,":[66],"we":[67],"study":[68],"an":[69,167],"extension":[70],"where":[74],"side":[75,100,142,164],"information":[76,101,165],"indicating":[77],"content":[78,92],"changes,":[79],"such":[80,99],"as":[81],"various":[82],"types":[83],"pings,":[86],"for":[87],"example,":[88],"signals":[89,111],"from":[90,147],"sitemaps,":[91],"delivery":[93],"networks,":[94],"etc.,":[95],"available.":[97],"Incorporating":[98],"into":[102],"challenging,":[107],"because":[108],"(i)":[109,160],"can":[112,174],"be":[113,175],"noisy":[114,163],"with":[115,120],"false":[116],"positive":[117],"events":[118],"missing":[121],"events;":[123],"(ii)":[125,173],"crawler":[127],"should":[128],"achieve":[129],"fair":[131],"performance":[132],"over":[133,200],"regardless":[136],"quality":[139],"information,":[143],"which":[144,159],"might":[145],"differ":[146],"page.":[152],"We":[153],"propose":[154],"scalable":[156],"algorithm":[158],"uses":[161],"in":[166,195],"way":[169],"under":[170],"mild":[171],"assumptions;":[172],"deployed":[176],"without":[177,193,217],"heavy":[178],"centralized":[179,218],"computation;":[180],"(iii)":[181],"able":[183],"crawl":[185],"at":[188],"constant":[190],"total":[191,197,214],"rate":[192],"spikes":[194],"usage":[199],"any":[201],"time":[202],"interval,":[203],"automatically":[205],"adapt":[206],"new":[209],"solution":[211],"changes":[216],"computation.":[219],"Experiments":[220],"clearly":[221],"demonstrate":[222],"versatility":[224],"our":[226],"approach.":[227]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}