{"id":"https://openalex.org/W3153326528","doi":"https://doi.org/10.1145/3442381.3450050","title":"Towards Realistic and ReproducibleWeb Crawl Measurements","display_name":"Towards Realistic and ReproducibleWeb Crawl Measurements","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3153326528","doi":"https://doi.org/10.1145/3442381.3450050","mag":"3153326528"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3450050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450050","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":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3450050","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087177121","display_name":"Jordan Jueckstock","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jordan Jueckstock","raw_affiliation_strings":["North Carolina State University, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044901966","display_name":"Shaown Sarker","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaown Sarker","raw_affiliation_strings":["North Carolina State University, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067856099","display_name":"Peter Snyder","orcid":"https://orcid.org/0000-0001-7880-2503"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Snyder","raw_affiliation_strings":["Brave Software, USA"],"affiliations":[{"raw_affiliation_string":"Brave Software, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077280647","display_name":"Aidan Beggs","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aidan Beggs","raw_affiliation_strings":["North Carolina State University, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647298","display_name":"Panagiotis Papadopoulos","orcid":"https://orcid.org/0000-0002-1928-6534"},"institutions":[{"id":"https://openalex.org/I4210096192","display_name":"Telef\u00f3nica (United Kingdom)","ror":"https://ror.org/00v9tt762","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210096192","https://openalex.org/I4210097190"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Panagiotis Papadopoulos","raw_affiliation_strings":["Telefonica Research, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Telefonica Research, United Kingdom","institution_ids":["https://openalex.org/I4210096192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086009737","display_name":"Matteo Varvello","orcid":"https://orcid.org/0000-0001-8500-4630"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matteo Varvello","raw_affiliation_strings":["Nokia Bell Labs, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068390911","display_name":"Benjamin Livshits","orcid":"https://orcid.org/0000-0002-4921-8452"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Benjamin Livshits","raw_affiliation_strings":["Brave Software and Imperial College London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Brave Software and Imperial College London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041544321","display_name":"Alexandros Kapravelos","orcid":"https://orcid.org/0000-0002-8839-8521"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandros Kapravelos","raw_affiliation_strings":["North Carolina State University, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5087177121"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":3.9614,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94536849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"80","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9990000128746033,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9987000226974487,"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":0.5717789530754089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33445656299591064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5717789530754089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33445656299591064}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442381.3450050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450050","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":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3442381.3450050","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3450050","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":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1995973276","https://openalex.org/W2043780693","https://openalex.org/W2099474262","https://openalex.org/W2113000322","https://openalex.org/W2148931201","https://openalex.org/W2159764755","https://openalex.org/W2342606171","https://openalex.org/W2403389194","https://openalex.org/W2424402128","https://openalex.org/W2535603283","https://openalex.org/W2742620100","https://openalex.org/W2769181731","https://openalex.org/W2807036284","https://openalex.org/W2904027722","https://openalex.org/W2933056782","https://openalex.org/W2957547225","https://openalex.org/W2962940036","https://openalex.org/W2980614388","https://openalex.org/W2980770947","https://openalex.org/W3004148183","https://openalex.org/W4298134634"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Accurate":[0],"web":[1,23,31,53,81,85,105,169],"measurement":[2,38,41,106],"is":[3,116],"critical":[4],"for":[5,44],"understanding":[6],"and":[7,10,55,87,95,136,140,179,184],"improving":[8],"security":[9,56,88],"privacy":[11,54,86],"online.":[12],"Such":[13],"measurements":[14,61,89],"implicitly":[15],"assume":[16],"that":[17,100],"automated":[18],"crawls":[19],"generalize":[20],"to":[21,72,147],"typical":[22],"user":[24,111],"experience.":[25],"But":[26],"anecdotal":[27],"evidence":[28],"suggests":[29],"the":[30,50,77,113,142,167],"behaves":[32],"differently":[33],"when":[34,63],"seen":[35],"via":[36],"well-known":[37],"endpoints":[39],"or":[40],"automation":[42],"frameworks,":[43],"various":[45],"reasons.":[46],"Our":[47],"work":[48],"improves":[49],"state":[51],"of":[52,133,145,149],"by":[57,92],"investigating":[58],"how":[59],"key":[60],"differ":[62],"using":[64],"naive":[65],"crawling":[66],"tool":[67],"defaults":[68],"vs.":[69],"careful":[70],"attempts":[71],"match":[73,108],"\u201creal\u201d":[74],"users":[75],"across":[76],"Tranco":[78],"top":[79],"25k":[80],"domains.":[82],"We":[83,98,155],"find":[84,125,156],"significantly":[90],"affected":[91],"vantage":[93,158],"point":[94,159],"browser":[96,126],"configuration.":[97],"conclude":[99],"unless":[101],"researchers":[102],"ensure":[103,172],"their":[104],"tools":[107],"real":[109],"world":[110],"experience,":[112],"research":[114],"community":[115],"likely":[117],"missing":[118],"important":[119],"signals":[120],"systematically.":[121],"For":[122],"example,":[123],"we":[124,174],"configuration":[127],"alone":[128],"causing":[129],"shifts":[130],"in":[131],"19%":[132],"known":[134],"ad":[135],"tracking":[137],"domains":[138],"encountered":[139],"altering":[141],"loading":[143],"frequency":[144],"up":[146],"10%":[148],"distinct":[150],"JavaScript":[151],"code":[152,183],"units":[153],"executed.":[154],"network":[157],"having":[160],"similar,":[161],"though":[162],"less":[163],"dramatic,":[164],"effects":[165],"on":[166],"same":[168],"metrics.":[170],"To":[171],"reproducibility,":[173],"carefully":[175],"document":[176],"our":[177,182],"methodology":[178],"publish":[180],"both":[181],"collected":[185],"data.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}