{"paper":{"title":"A Graph-structured Dataset for Wikipedia Research","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.IR","authors_text":"Benjamin Ricaud, Nicolas Aspert, Pierre Vandergheynst, Volodymyr Miz","submitted_at":"2019-03-20T16:31:29Z","abstract_excerpt":"Wikipedia is a rich and invaluable source of information. Its central place on the Web makes it a particularly interesting object of study for scientists. Researchers from different domains used various complex datasets related to Wikipedia to study language, social behavior, knowledge organization, and network theory. While being a scientific treasure, the large size of the dataset hinders pre-processing and may be a challenging obstacle for potential new studies. This issue is particularly acute in scientific domains where researchers may not be technically and data processing savvy. On one "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08597","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":""},"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"}