{"id":"https://openalex.org/W7152507863","doi":"https://doi.org/10.1145/3774904.3792814","title":"URLBank: Data-Driven URL Discovery via Temporal Link Graphs","display_name":"URLBank: Data-Driven URL Discovery via Temporal Link Graphs","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152507863","doi":"https://doi.org/10.1145/3774904.3792814"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792814","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792814","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089437630","display_name":"Felipe Marineli","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Felipe Marineli","raw_affiliation_strings":["Roma Tre University, Rome, Italy and Meltwater Deutschland GmbH, Berlin, Germany"],"raw_orcid":"https://orcid.org/0009-0002-6577-5491","affiliations":[{"raw_affiliation_string":"Roma Tre University, Rome, Italy and Meltwater Deutschland GmbH, Berlin, Germany","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044386001","display_name":"Valerio Cetorelli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107357","display_name":"The Meltech (United Kingdom)","ror":"https://ror.org/01vqxw943","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107357"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Valerio Cetorelli","raw_affiliation_strings":["Meltwater (UK) Ltd, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-5406-702X","affiliations":[{"raw_affiliation_string":"Meltwater (UK) Ltd, London, United Kingdom","institution_ids":["https://openalex.org/I4210107357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030700727","display_name":"Valter Crescenzi","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valter Crescenzi","raw_affiliation_strings":["Roma Tre University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7266-6755","affiliations":[{"raw_affiliation_string":"Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113511969","display_name":"Tim Furche","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107357","display_name":"The Meltech (United Kingdom)","ror":"https://ror.org/01vqxw943","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107357"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Furche","raw_affiliation_strings":["Meltwater (UK) Ltd, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3918-3807","affiliations":[{"raw_affiliation_string":"Meltwater (UK) Ltd, London, United Kingdom","institution_ids":["https://openalex.org/I4210107357"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaonan Guo","orcid":"https://orcid.org/0009-0005-0588-4743"},"institutions":[{"id":"https://openalex.org/I4210107357","display_name":"The Meltech (United Kingdom)","ror":"https://ror.org/01vqxw943","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107357"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaonan Guo","raw_affiliation_strings":["Meltwater (UK) Ltd, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0005-0588-4743","affiliations":[{"raw_affiliation_string":"Meltwater (UK) Ltd, London, United Kingdom","institution_ids":["https://openalex.org/I4210107357"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7914","last_page":"7922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.15459999442100525,"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":0.15459999442100525,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.10209999978542328,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0966000035405159,"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/link","display_name":"Link (geometry)","score":0.32030001282691956},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.27549999952316284},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2721000015735626},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2612000107765198},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.2418999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6474000215530396},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2418999969959259},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24079999327659607}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792814","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792814","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1494146631","https://openalex.org/W1680189815","https://openalex.org/W1976216148","https://openalex.org/W2005579877","https://openalex.org/W2005646337","https://openalex.org/W2013469079","https://openalex.org/W2014766608","https://openalex.org/W2049582451","https://openalex.org/W2054637307","https://openalex.org/W2055950890","https://openalex.org/W2068410751","https://openalex.org/W2099585315","https://openalex.org/W2105803339","https://openalex.org/W2110034127","https://openalex.org/W2151007976","https://openalex.org/W2154445423","https://openalex.org/W2158420658","https://openalex.org/W2294114862","https://openalex.org/W2296164608","https://openalex.org/W2619657783","https://openalex.org/W2743928556","https://openalex.org/W2912918933","https://openalex.org/W3197688135","https://openalex.org/W4205184193","https://openalex.org/W4240971155"],"related_works":[],"abstract_inverted_index":{"Web-scale":[0],"editorial":[1],"crawling":[2],"must":[3],"balance":[4],"coverage":[5,77,108],"and":[6,11,94,129,137,160],"freshness":[7],"within":[8],"tight":[9],"politeness":[10],"request":[12],"budgets.":[13],"Nonetheless,":[14],"in":[15,155],"production":[16,116],"systems,":[17],"manual":[18,34],"seed":[19,43],"management":[20],"remains":[21],"common":[22],"despite":[23],"being":[24],"inefficient\u2014oversampling":[25],"redundant":[26],"seeds":[27],"while":[28],"missing":[29],"high-yield":[30],"ones.":[31],"URLBank":[32,87,119],"replaces":[33],"curation":[35],"with":[36,109,121],"a":[37,75,80],"label-free":[38],"controller":[39],"that":[40,143],"infers":[41],"optimal":[42],"selection":[44],"directly":[45],"from":[46],"temporal":[47,144],"crawl":[48,127],"telemetry.":[49],"It":[50],"identifies":[51],"candidate":[52],"entry":[53],"points,":[54],"estimates":[55],"stability\u2014the":[56],"persistence":[57],"of":[58,65],"links":[59],"across":[60,103],"crawler":[61,117],"revolutions\u2014and":[62],"productivity\u2014the":[63],"rate":[64],"first-seen":[66],"publications\u2014and":[67],"ranks":[68],"them":[69],"through":[70,146],"greedy":[71,149],"marginal":[72],"gain":[73],"on":[74],"shared-credit":[76],"objective.":[78],"In":[79],"shadow":[81],"A/B":[82],"evaluation":[83],"spanning":[84],"5,238":[85],"sites,":[86],"consistently":[88],"achieves":[89],"higher":[90],"coverage,":[91,157],"greater":[92],"efficiency,":[93,159],"earlier":[95],"discovery":[96],"under":[97],"identical":[98],"conditions.":[99],"Gains":[100],"remain":[101],"stable":[102],"Top-K":[104],"budgets,":[105,128],"approaching":[106],"near-complete":[107],"far":[110],"fewer":[111],"seeds.":[112],"Deployed":[113],"alongside":[114],"Meltwater's":[115],"Pulitzer,":[118],"operates":[120],"versioned":[122],"policies,":[123],"ranked":[124],"prefixes":[125],"for":[126],"integrated":[130],"health":[131],"diagnostics,":[132],"making":[133],"allocation":[134],"transparent,":[135],"auditable,":[136],"reversible.":[138],"Together,":[139],"these":[140],"results":[141],"demonstrate":[142],"signals,":[145],"an":[147],"interpretable":[148],"objective,":[150],"yield":[151],"large,":[152],"measurable":[153],"improvements":[154],"industrial-scale":[156],"resource":[158],"freshness.":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-10T00:00:00"}