{"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/the-semantic-scholar-open-data-platform","title":"The Semantic Scholar Open Data Platform","arxiv_id":"2301.10140","date":"2023-01-24","proceeding":null,"authors":["Rodney Kinney","Chloe Anastasiades","Russell Authur","Iz Beltagy","Jonathan Bragg","Alexandra Buraczynski","Isabel Cachola","Stefan Candra","Yoganand Chandrasekhar","Arman Cohan","Miles Crawford","Doug Downey","Jason Dunkelberger","Oren Etzioni","Rob Evans","Sergey Feldman","Joseph Gorney","David Graham","Fangzhou Hu","Regan Huff","Daniel King","Sebastian Kohlmeier","Bailey Kuehl","Michael Langan","Daniel Lin","Haokun Liu","Kyle Lo","Jaron Lochner","Kelsey MacMillan","Tyler Murray","Chris Newell","Smita Rao","Shaurya Rohatgi","Paul Sayre","Zejiang Shen","Amanpreet Singh","Luca Soldaini","Shivashankar Subramanian","Amber Tanaka","Alex D. Wade","Linda Wagner","Lucy Lu Wang","Chris Wilhelm","Caroline Wu","Jiangjiang Yang","Angele Zamarron","Madeleine van Zuylen","Daniel S. Weld"],"abstract":"The volume of scientific output is creating an urgent need for automated tools to help scientists keep up with developments in their field. Semantic Scholar (S2) is an open data platform and website aimed at accelerating science by helping scholars discover and understand scientific literature. We combine public and proprietary data sources using state-of-the-art techniques for scholarly PDF content extraction and automatic knowledge graph construction to build the Semantic Scholar Academic Graph, the largest open scientific literature graph to-date, with 200M+ papers, 80M+ authors, 550M+ paper-authorship edges, and 2.4B+ citation edges. The graph includes advanced semantic features such as structurally parsed text, natural language summaries, and vector embeddings. In this paper, we describe the components of the S2 data processing pipeline and the associated APIs offered by the platform. We will update this living document to reflect changes as we add new data offerings and improve existing services.","url_abs":"https://arxiv.org/abs/2301.10140v2","url_pdf":"https://arxiv.org/pdf/2301.10140v2.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":"the-semantic-scholar-open-data-platform","repo_url":"https://github.com/allenai/s2aff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.10140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.10140"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/s2aff","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b6270ab42d807275","entry":"build_query_ngrams","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/features.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b6270ab42d807275"}},{"code_sha256_prefix":"a6dae4dd5461e7ab","entry":"coerce_v2_to_v1like","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/ror.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/ror.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6dae4dd5461e7ab"}},{"code_sha256_prefix":"a3b94dceef736662","entry":"format_group","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/lightgbm_helpers.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/lightgbm_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3b94dceef736662"}},{"code_sha256_prefix":"63b8d6ba9fb53208","entry":"get_stage1_pipeline","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/flags.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/flags.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63b8d6ba9fb53208"}},{"code_sha256_prefix":"a923f8dd990aa916","entry":"get_stage2_pipeline","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/flags.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/flags.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a923f8dd990aa916"}},{"code_sha256_prefix":"6bcc20d86535a8aa","entry":"normalize_geoname_id","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/text.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/text.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6bcc20d86535a8aa"}},{"code_sha256_prefix":"ae988508ee1cc8ac","entry":"sum_list_of_list_of_tuples","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/ror.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/ror.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ae988508ee1cc8ac"}},{"code_sha256_prefix":"2f31deaa2df92981","entry":"url_to_filename","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/file_cache.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/file_cache.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f31deaa2df92981"}},{"code_sha256_prefix":"06fb62360ea56104","entry":"v2_display_name","repo":"allenai/s2aff","repo_kind":"official","path":"s2aff/ror.py","file_url":"https://github.com/allenai/s2aff/blob/HEAD/s2aff/ror.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"06fb62360ea56104"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}