{"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/elsevier-oa-cc-by-corpus","title":"Elsevier OA CC-By Corpus","arxiv_id":"2008.00774","date":"2020-08-03","proceeding":null,"authors":["Daniel Kershaw","Rob Koeling"],"abstract":"We introduce the Elsevier OA CC-BY corpus. This is the first open corpus of Scientific Research papers which has a representative sample from across scientific disciplines. This corpus not only includes the full text of the article, but also the metadata of the documents, along with the bibliographic information for each reference.","url_abs":"https://arxiv.org/abs/2008.00774v3","url_pdf":"https://arxiv.org/pdf/2008.00774v3.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":[],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"elsevier-oa-cc-by","name":"Elsevier OA CC-BY","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.00774","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}