{"id":"https://openalex.org/W4416502100","doi":"https://doi.org/10.1145/3730567.3764507","title":"Toward Better Efficiency vs. Fidelity Tradeoffs in Web Archives","display_name":"Toward Better Efficiency vs. Fidelity Tradeoffs in Web Archives","publication_year":2025,"publication_date":"2025-10-28","ids":{"openalex":"https://openalex.org/W4416502100","doi":"https://doi.org/10.1145/3730567.3764507"},"language":null,"primary_location":{"id":"doi:10.1145/3730567.3764507","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3764507","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 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3730567.3764507","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064848672","display_name":"Jingyuan Zhu","orcid":"https://orcid.org/0000-0002-3724-3298"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jingyuan Zhu","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"raw_orcid":"https://orcid.org/0000-0002-3724-3298","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huanchen Sun","orcid":"https://orcid.org/0009-0004-5558-7475"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huanchen Sun","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0009-0004-5558-7475","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":null,"display_name":"Harsha V. Madhyastha","orcid":"https://orcid.org/0009-0000-3921-5680"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harsha V. Madhyastha","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0009-0000-3921-5680","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064848672"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47510696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1025","last_page":"1031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9639999866485596,"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":0.9639999866485596,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.005200000014156103,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/scripting-language","display_name":"Scripting language","score":0.6514000296592712},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.519599974155426},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5076000094413757},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.38420000672340393},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3061000108718872},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.30489999055862427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127000093460083},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7056000232696533},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6514000296592712},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38940000534057617},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3061000108718872},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.30489999055862427},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C100158260","wikidata":"https://www.wikidata.org/wiki/Q1650567","display_name":"Dynamic web page","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3730567.3764507","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3764507","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 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3730567.3764507","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3764507","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 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1613836731","https://openalex.org/W1991548210","https://openalex.org/W2017726337","https://openalex.org/W2040427982","https://openalex.org/W2086658401","https://openalex.org/W2148931201","https://openalex.org/W2149586775","https://openalex.org/W2221766821","https://openalex.org/W2295141584","https://openalex.org/W2559656577","https://openalex.org/W2787523452","https://openalex.org/W2904027722","https://openalex.org/W3176232489","https://openalex.org/W4387316191"],"related_works":[],"abstract_inverted_index":{"Operators":[0],"of":[1,20],"web":[2],"archives":[3],"have":[4],"two":[5],"options":[6],"for":[7],"how":[8],"to":[9],"crawl":[10],"pages":[11],"from":[12],"the":[13,21],"web.":[14],"Browser-based":[15],"dynamic":[16],"crawlers":[17,33],"capture":[18],"all":[19],"resources":[22,40],"on":[23],"every":[24],"page,":[25],"but":[26,37],"incur":[27],"high":[28],"compute":[29],"overheads.":[30],"Static":[31],"browserless":[32],"are":[34,42,47],"more":[35],"lightweight,":[36],"miss":[38],"page":[39],"which":[41],"fetched":[43],"only":[44],"when":[45],"scripts":[46],"executed.":[48]},"counts_by_year":[],"updated_date":"2025-11-28T15:57:32.215526","created_date":"2025-11-23T00:00:00"}
