{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:07:03Z","timestamp":1764018423720,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"National Science Foundation","award":["2403432"],"award-info":[{"award-number":["2403432"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,28]]},"DOI":"10.1145\/3730567.3764507","type":"proceedings-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T15:22:38Z","timestamp":1763738558000},"page":"1025-1031","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward Better Efficiency vs. Fidelity Tradeoffs in Web Archives"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3724-3298","authenticated-orcid":false,"given":"Jingyuan","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5558-7475","authenticated-orcid":false,"given":"Huanchen","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3921-5680","authenticated-orcid":false,"given":"Harsha V.","family":"Madhyastha","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Amazon Go. https:\/\/www.amazon.jobs\/content\/en\/teams\/worldwide-grocerystores\/amazon-go."},{"key":"e_1_3_2_1_2_1","unstructured":"Bolt Design System. https:\/\/boltdesignsystem.com\/pattern-lab\/patterns\/40-components-code-snippet-10-code-snippet-language\/40-components-codesnippet-10-code-snippet-language.html\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Bolt Design System. https:\/\/web.archive.org\/web\/20250218130712\/https:\/\/boltdesignsystem.com\/pattern-lab\/patterns\/40-components-code-snippet- 10-code-snippet-language\/40-components-code-snippet-10-code-snippetlanguage.html\/."},{"key":"e_1_3_2_1_4_1","unstructured":"Browsertrix Crawler. https:\/\/github.com\/webrecorder\/browsertrix-crawler."},{"key":"e_1_3_2_1_5_1","unstructured":"Critical rendering path - Performance | MDN. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/Performance\/Guides\/Critical_rendering_path."},{"key":"e_1_3_2_1_6_1","unstructured":"GitHub - ArchiveBox\/ArchiveBox: Open source self-hosted web archiving. https:\/\/github.com\/ArchiveBox\/ArchiveBox."},{"key":"e_1_3_2_1_7_1","unstructured":"GitHub - internetarchive\/brozzler: brozzler - distributed browser-based web crawler \u2014 github.com. https:\/\/github.com\/internetarchive\/brozzler."},{"key":"e_1_3_2_1_8_1","unstructured":"GitHub - internetarchive\/heritrix3: Heritrix is the Internet Archive's open-source extensible web-scale archival-quality web crawler project. https:\/\/github.com\/internetarchive\/heritrix3."},{"key":"e_1_3_2_1_9_1","unstructured":"Japanese Kit Kat: Chocolate Orange \u2014 bokksumarket.com. https:\/\/www.bokksumarket.com\/collections\/best-seller\/products\/japanese-kitkat-choco-orange."},{"key":"e_1_3_2_1_10_1","unstructured":"Next.js by Vercel - The React Framework \u2014 nextjs.org. https:\/\/nextjs.org\/."},{"key":"e_1_3_2_1_11_1","unstructured":"pywb\/pywb\/rules.yaml at main \u00b7 webrecorder\/pywb. https:\/\/github.com\/webrecorder\/pywb\/blob\/main\/pywb\/rules.yaml."},{"key":"e_1_3_2_1_12_1","unstructured":"Review Crawl Quality - Browsertrix Docs. https:\/\/docs.browsertrix.com\/userguide\/review\/."},{"key":"e_1_3_2_1_13_1","unstructured":"third_party\/blink\/renderer\/core\/layout\/layout_object.h-chromium\/src-Git at Google. https:\/\/chromium.googlesource.com\/chromium\/src\/\/refs\/heads\/main\/third_party\/blink\/renderer\/core\/layout\/layout_object.h."},{"key":"e_1_3_2_1_14_1","unstructured":"Usage\u2014pywb 2.7 documentation. https:\/\/pywb.readthedocs.io\/en\/latest\/manual\/usage.html#http-s-proxy-mode-access."},{"key":"e_1_3_2_1_15_1","unstructured":"The WARC Format 1.1. https:\/\/iipc.github.io\/warc-specifications\/specifications\/warc-format\/warc-1.1\/."},{"key":"e_1_3_2_1_16_1","unstructured":"Webrecorder. https:\/\/webrecorder.net\/."},{"key":"e_1_3_2_1_17_1","unstructured":"webrecorder\/pywb: Core PythonWeb Archiving Toolkit for replay and recording of web archives. https:\/\/github.com\/webrecorder\/pywb."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498759.1498837"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511466"},{"key":"e_1_3_2_1_20_1","volume-title":"Martin Van den Berg, and Byron Dom","author":"Chakrabarti Soumen","year":"1999","unstructured":"Soumen Chakrabarti, Martin Van den Berg, and Byron Dom. 1999. Focused crawling: a new approach to topic-specific Web resource discovery. Computer networks 31, 11--16 (1999), 1623--1640."},{"key":"e_1_3_2_1_21_1","unstructured":"Junghoo Cho and Hector Garcia-Molina. 1999. The evolution of the web and implications for an incremental crawler. Technical Report. Stanford."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511464"},{"key":"e_1_3_2_1_23_1","unstructured":"Michelangelo Diligenti Frans Coetzee Steve Lawrence C Lee Giles Marco Gori et al. 2000. Focused Crawling Using Context Graphs.. In VLDB. Citeseer 527--534."},{"key":"e_1_3_2_1_24_1","volume-title":"Sprinter: Speeding Up High-Fidelity Crawling of the ModernWeb. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Goel Ayush","year":"2024","unstructured":"Ayush Goel, Jingyuan Zhu, Ravi Netravali, and Harsha V Madhyastha. 2024. Sprinter: Speeding Up High-Fidelity Crawling of the ModernWeb. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 893--906."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019213109274"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0167475"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511484"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741114"},{"key":"e_1_3_2_1_29_1","volume-title":"Silo: Exploiting JavaScript and DOM Storage for Faster Page Loads. In USENIX Conference on Web Application Development (WebApps 10)","author":"Mickens James","year":"2010","unstructured":"James Mickens. 2010. Silo: Exploiting JavaScript and DOM Storage for Faster Page Loads. In USENIX Conference on Web Application Development (WebApps 10)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177102.3177118"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23386"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2307636.2307649"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3466866"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/602421.602422"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL57899.2023.00022"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493484"},{"key":"e_1_3_2_1_37_1","volume-title":"The Paper of Record Meets an Ephemeral Web: An Examination of Linkrot and Content Drift within The New York Times. Available at SSRN 3833133","author":"Zittrain Jonathan L","year":"2021","unstructured":"Jonathan L Zittrain, John Bowers, and Clare Stanton. 2021. The Paper of Record Meets an Ephemeral Web: An Examination of Linkrot and Content Drift within The New York Times. Available at SSRN 3833133 (2021)."}],"event":{"name":"IMC '25:ACM Internet Measurement Conference","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGCOMM ACM Special Interest Group on Data Communication"],"location":"Madison WI USA"},"container-title":["Proceedings of the 2025 ACM Internet Measurement Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3730567.3764507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:06:25Z","timestamp":1764018385000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3730567.3764507"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":37,"alternative-id":["10.1145\/3730567.3764507","10.1145\/3730567"],"URL":"https:\/\/doi.org\/10.1145\/3730567.3764507","relation":{},"subject":[],"published":{"date-parts":[[2025,10,28]]},"assertion":[{"value":"2025-11-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}