{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BBQ3P6FU6T3HOJRBRLQYMVMJ4J","short_pith_number":"pith:BBQ3P6FU","schema_version":"1.0","canonical_sha256":"0861b7f8b4f4f67726218ae1865589e250eb928ac45d5a3aad653fb8b1b260e0","source":{"kind":"arxiv","id":"2301.10140","version":2},"attestation_state":"computed","paper":{"title":"The Semantic Scholar Open Data Platform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Alexandra Buraczynski, Alex D. Wade, Amanpreet Singh, Amber Tanaka, Angele Zamarron, Arman Cohan, Bailey Kuehl, Caroline Wu, Chloe Anastasiades, Chris Newell, Chris Wilhelm, Daniel King, Daniel Lin, Daniel S. Weld, David Graham, Doug Downey, Fangzhou Hu, Haokun Liu, Isabel Cachola, Iz Beltagy, Jaron Lochner, Jason Dunkelberger, Jiangjiang Yang, Jonathan Bragg, Joseph Gorney, Kelsey MacMillan, Kyle Lo, Linda Wagner, Luca Soldaini, Lucy Lu Wang, Madeleine van Zuylen, Michael Langan, Miles Crawford, Oren Etzioni, Paul Sayre, Regan Huff, Rob Evans, Rodney Kinney, Russell Authur, Sebastian Kohlmeier, Sergey Feldman, Shaurya Rohatgi, Shivashankar Subramanian, Smita Rao, Stefan Candra, Tyler Murray, Yoganand Chandrasekhar, Zejiang Shen","submitted_at":"2023-01-24T17:13:08Z","abstract_excerpt":"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+ pape"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.10140","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2023-01-24T17:13:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e05880156e590ebf7b1f82239730d8e6d061b4b07a49a4236631689d26f61c78","abstract_canon_sha256":"c75454c07915df6b165bf23e98e09d98ab0d2644957a3affe23cdabc59fdcd79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:10.132609Z","signature_b64":"naw3cxYYz7ZO91E3r0mQYl8SN8eTZIDH/AtJIPvqBCWBqVMKg4ceBo4X1uLdNjfshHM19Bbc1brGlCb2zdLuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0861b7f8b4f4f67726218ae1865589e250eb928ac45d5a3aad653fb8b1b260e0","last_reissued_at":"2026-07-05T10:54:10.132111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:10.132111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Semantic Scholar Open Data Platform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Alexandra Buraczynski, Alex D. Wade, Amanpreet Singh, Amber Tanaka, Angele Zamarron, Arman Cohan, Bailey Kuehl, Caroline Wu, Chloe Anastasiades, Chris Newell, Chris Wilhelm, Daniel King, Daniel Lin, Daniel S. Weld, David Graham, Doug Downey, Fangzhou Hu, Haokun Liu, Isabel Cachola, Iz Beltagy, Jaron Lochner, Jason Dunkelberger, Jiangjiang Yang, Jonathan Bragg, Joseph Gorney, Kelsey MacMillan, Kyle Lo, Linda Wagner, Luca Soldaini, Lucy Lu Wang, Madeleine van Zuylen, Michael Langan, Miles Crawford, Oren Etzioni, Paul Sayre, Regan Huff, Rob Evans, Rodney Kinney, Russell Authur, Sebastian Kohlmeier, Sergey Feldman, Shaurya Rohatgi, Shivashankar Subramanian, Smita Rao, Stefan Candra, Tyler Murray, Yoganand Chandrasekhar, Zejiang Shen","submitted_at":"2023-01-24T17:13:08Z","abstract_excerpt":"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+ pape"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10140","kind":"arxiv","version":2},"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/2301.10140/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.10140","created_at":"2026-07-05T10:54:10.132166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.10140v2","created_at":"2026-07-05T10:54:10.132166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10140","created_at":"2026-07-05T10:54:10.132166+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBQ3P6FU6T3H","created_at":"2026-07-05T10:54:10.132166+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBQ3P6FU6T3HOJRB","created_at":"2026-07-05T10:54:10.132166+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBQ3P6FU","created_at":"2026-07-05T10:54:10.132166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08348","citing_title":"Works on My QPU: Reproducibility in Quantum Computing Research","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18874","citing_title":"Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02416","citing_title":"The Future of NLP may not be at NLP Conferences: Scholarly Migration Patterns in Natural Language Processing","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05443","citing_title":"MIRAI: Prediction and Generation of High-Impact Academic Research","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28120","citing_title":"The Reciprocal Impact of Science and Software: A Cross-Corpus Analysis of How Research Shapes Software and Software Enables Research","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14790","citing_title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23694","citing_title":"ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28187","citing_title":"Whose Name Comes Up? III: Persona Prompting Effects in LLM-Based Scholar Recommendation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29234","citing_title":"Rethinking Literature Search Evaluation: Deep Research Helps, and Human Citation Lists Are Not a Ground Truth","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29522","citing_title":"DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23694","citing_title":"ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2409.14634","citing_title":"Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04459","citing_title":"Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20833","citing_title":"MemGym: a Long-Horizon Memory Environment for LLM Agents","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15474","citing_title":"Jobs' AI Exposure Should Be Measured from Evidence, Not Model Priors","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2508.20765","citing_title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00361","citing_title":"Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.07037","citing_title":"Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11258","citing_title":"Unlocking LLM Creativity in Science through Analogical Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23430","citing_title":"Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18874","citing_title":"How Adversarial Environments Mislead Agentic AI?","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07530","citing_title":"The Shrinking Lifespan of LLMs in Science","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08898","citing_title":"Omakase: proactive assistance with actionable suggestions for evolving scientific research projects","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12498","citing_title":"Lit2Vec: A Reproducible Workflow for Building a Legally Screened Chemistry Corpus from S2ORC for Downstream Retrieval and Text Mining","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J","json":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J.json","graph_json":"https://pith.science/api/pith-number/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/graph.json","events_json":"https://pith.science/api/pith-number/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/events.json","paper":"https://pith.science/paper/BBQ3P6FU"},"agent_actions":{"view_html":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J","download_json":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J.json","view_paper":"https://pith.science/paper/BBQ3P6FU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.10140&json=true","fetch_graph":"https://pith.science/api/pith-number/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/graph.json","fetch_events":"https://pith.science/api/pith-number/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/action/storage_attestation","attest_author":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/action/author_attestation","sign_citation":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/action/citation_signature","submit_replication":"https://pith.science/pith/BBQ3P6FU6T3HOJRBRLQYMVMJ4J/action/replication_record"}},"created_at":"2026-07-05T10:54:10.132166+00:00","updated_at":"2026-07-05T10:54:10.132166+00:00"}