{"paper":{"title":"Web Archive Analytics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.NI","cs.SI"],"primary_cat":"cs.DL","authors_text":"Benno Stein, Janek Bevendorff, Johannes Kiesel, Maik Fr\\\"obe, Martin Potthast, Matthias Hagen, Michael V\\\"olske","submitted_at":"2021-07-02T08:12:50Z","abstract_excerpt":"Web archive analytics is the exploitation of publicly accessible web pages and their evolution for research purposes -- to the extent organizationally possible for researchers. In order to better understand the complexity of this task, the first part of this paper puts the entirety of the world's captured, created, and replicated data (the \"Global Datasphere\") in relation to other important data sets such as the public internet and its web pages, or what is preserved thereof by the Internet Archive.\n  Recently, the Webis research group, a network of university chairs to which the authors belon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00893","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.00893/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}