{"id":"https://openalex.org/W2912826586","doi":"https://doi.org/10.1145/3308558.3313664","title":"PYTHIA","display_name":"PYTHIA","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2912826586","doi":"https://doi.org/10.1145/3308558.3313664","mag":"2912826586"},"language":"en","primary_location":{"id":"doi:10.1145/3308558.3313664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313664","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308558.3313664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079790457","display_name":"Srdjan Matic","orcid":"https://orcid.org/0000-0003-2822-3970"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Srdjan Matic","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023313904","display_name":"Gareth Tyson","orcid":"https://orcid.org/0000-0003-3010-791X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gareth Tyson","raw_affiliation_strings":["Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046881273","display_name":"Gianluca Stringhini","orcid":"https://orcid.org/0000-0002-6162-578X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gianluca Stringhini","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6817,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82304527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3072","last_page":"3078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998000264167786,"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":0.9998000264167786,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9995999932289124,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8302625417709351},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6563462018966675},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6049339771270752},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5439574122428894},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.5432218313217163},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5293574929237366},{"id":"https://openalex.org/keywords/content-delivery","display_name":"Content delivery","score":0.48271653056144714},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.45448634028434753},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4268401861190796},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3406696319580078},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.14887657761573792},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13411614298820496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09215453267097473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302625417709351},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6563462018966675},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6049339771270752},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5439574122428894},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.5432218313217163},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5293574929237366},{"id":"https://openalex.org/C2986847828","wikidata":"https://www.wikidata.org/wiki/Q269415","display_name":"Content delivery","level":2,"score":0.48271653056144714},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.45448634028434753},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4268401861190796},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3406696319580078},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.14887657761573792},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13411614298820496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09215453267097473},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3308558.3313664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313664","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.06925","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.06925","pdf_url":"https://arxiv.org/pdf/1903.06925","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-158331","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-158331","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3308558.3313664","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308558.3313664","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1510134550","https://openalex.org/W1999769581","https://openalex.org/W2029129836","https://openalex.org/W2048996446","https://openalex.org/W2054479920","https://openalex.org/W2077092541","https://openalex.org/W2090106845","https://openalex.org/W2127770188","https://openalex.org/W2154601295","https://openalex.org/W2164373098","https://openalex.org/W2221475113","https://openalex.org/W2300286844","https://openalex.org/W2464966933","https://openalex.org/W2507466050","https://openalex.org/W2603454751","https://openalex.org/W2604746202","https://openalex.org/W2785471540","https://openalex.org/W2796057488","https://openalex.org/W2886313391","https://openalex.org/W2963829720","https://openalex.org/W2963905788","https://openalex.org/W6630256003"],"related_works":["https://openalex.org/W2092530219","https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W2105580438","https://openalex.org/W2057435755","https://openalex.org/W3121798572","https://openalex.org/W2018782216","https://openalex.org/W1967387355","https://openalex.org/W2943958348"],"abstract_inverted_index":{"A":[0],"common":[1],"approach":[2,89],"when":[3],"setting":[4],"up":[5],"a":[6,55,61,86,114,160],"website":[7,57],"is":[8,58],"to":[9,50,112,133,186,190,195,198],"utilize":[10],"third":[11],"party":[12],"Web":[13,92,101,116,123],"hosting":[14],"and":[15,31,53,103,119,127,146,158,171,194],"content":[16,93,104],"delivery":[17,105],"networks.":[18,106],"Without":[19],"taking":[20],"this":[21,80],"trend":[22],"into":[23],"account,":[24],"any":[25],"measurement":[26],"study":[27],"inspecting":[28],"the":[29,40,110,153],"deployment":[30],"operation":[32],"of":[33,63,169,176],"websites":[34],"can":[35,47],"be":[36,48],"heavily":[37],"skewed.":[38],"Unfortunately,":[39],"research":[41],"community":[42],"lacks":[43],"generalizable":[44],"tools":[45],"that":[46,173],"used":[49],"identify":[51],"how":[52],"where":[54],"given":[56,115],"hosted.":[59],"Instead,":[60],"number":[62],"ad":[64],"hoc":[65],"techniques":[66],"have":[67],"emerged,":[68],"e.g.,":[69],"using":[70],"Autonomous":[71],"System":[72],"databases,":[73],"domain":[74],"prefixes":[75],"for":[76,90],"CNAME":[77],"records.":[78],"In":[79],"work":[81],"we":[82,140],"propose":[83],"Pythia":[84],",":[85],"novel":[87],"lightweight":[88],"identifying":[91],"hosted":[94],"on":[95,143],"third-party":[96,131],"infrastructures,":[97],"including":[98],"both":[99,150],"traditional":[100],"hosts":[102],"Our":[107,164],"framework":[108,139],"identifies":[109],"organization":[111],"which":[113,122,128],"page":[117],"belongs,":[118],"it":[120,142,197],"detects":[121,172],"servers":[124],"are":[125,179],"self-hosted":[126],"ones":[129],"leverage":[130],"services":[132,157],"provide":[134],"contents.":[135],"To":[136],"test":[137],"our":[138,184,192],"run":[141],"40,000":[144],"URLs":[145],"evaluate":[147],"its":[148],"accuracy,":[149],"by":[151],"comparing":[152],"results":[154],"with":[155,159],"similar":[156],"manually":[161],"validated":[162],"groundtruth.":[163],"tool":[165,185],"achieves":[166],"an":[167],"accuracy":[168],"90%":[170],"under":[174],"11%":[175],"popular":[177],"domains":[178],"self-hosted.":[180],"We":[181],"publicly":[182],"release":[183],"allow":[187],"other":[188],"researchers":[189],"reproduce":[191],"findings,":[193],"apply":[196],"their":[199],"own":[200],"studies.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2019-02-21T00:00:00"}
