{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gorc-a-large-contextual-citation-graph-of","title":"S2ORC: The Semantic Scholar Open Research Corpus","arxiv_id":"1911.02782","date":"2019-11-07","proceeding":"ACL 2020 6","authors":["Kyle Lo","Lucy Lu Wang","Mark Neumann","Rodney Kinney","Dan S. Weld"],"abstract":"We introduce S2ORC, a large corpus of 81.1M English-language academic papers spanning many academic disciplines. The corpus consists of rich metadata, paper abstracts, resolved bibliographic references, as well as structured full text for 8.1M open access papers. Full text is annotated with automatically-detected inline mentions of citations, figures, and tables, each linked to their corresponding paper objects. In S2ORC, we aggregate papers from hundreds of academic publishers and digital archives into a unified source, and create the largest publicly-available collection of machine-readable academic text to date. We hope this resource will facilitate research and development of tools and tasks for text mining over academic text.","url_abs":"https://arxiv.org/abs/1911.02782v3","url_pdf":"https://arxiv.org/pdf/1911.02782v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gorc-a-large-contextual-citation-graph-of","repo_url":"https://github.com/allenai/s2orc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"gorc-a-large-contextual-citation-graph-of","repo_url":"https://github.com/allenai/s2-gorc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[{"slug":"s2orc","name":"S2ORC","full_name":"S2ORC"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.02782","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}