{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JD3F7SA75BOY4QB26VLB6LAIY5","short_pith_number":"pith:JD3F7SA7","schema_version":"1.0","canonical_sha256":"48f65fc81fe85d8e403af5561f2c08c77e4c81c598015b7e8a6582303406379c","source":{"kind":"arxiv","id":"1911.02782","version":3},"attestation_state":"computed","paper":{"title":"S2ORC: The Semantic Scholar Open Research Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"Dan S. Weld, Kyle Lo, Lucy Lu Wang, Mark Neumann, Rodney Kinney","submitted_at":"2019-11-07T07:34:43Z","abstract_excerpt":"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 "},"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":"1911.02782","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-07T07:34:43Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"738f8a9a5cb610e98d7573c8998f7668acd28282bd46234ab44ba4389a280884","abstract_canon_sha256":"8f10ff8018bf41e237d7d41a22a416cc531822c7914b3fbac480dd087a01205c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:41.749267Z","signature_b64":"qImxSt8f4Wws08M+WFtj1FCYfnGjL7mXS1aDjqHzrB4AdBp+iNqYT5lK+Y7dQRewt636gRAaKuxoepX1wnTaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48f65fc81fe85d8e403af5561f2c08c77e4c81c598015b7e8a6582303406379c","last_reissued_at":"2026-07-05T01:16:41.748645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:41.748645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S2ORC: The Semantic Scholar Open Research Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"Dan S. Weld, Kyle Lo, Lucy Lu Wang, Mark Neumann, Rodney Kinney","submitted_at":"2019-11-07T07:34:43Z","abstract_excerpt":"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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.02782","kind":"arxiv","version":3},"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/1911.02782/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":"1911.02782","created_at":"2026-07-05T01:16:41.748822+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.02782v3","created_at":"2026-07-05T01:16:41.748822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.02782","created_at":"2026-07-05T01:16:41.748822+00:00"},{"alias_kind":"pith_short_12","alias_value":"JD3F7SA75BOY","created_at":"2026-07-05T01:16:41.748822+00:00"},{"alias_kind":"pith_short_16","alias_value":"JD3F7SA75BOY4QB2","created_at":"2026-07-05T01:16:41.748822+00:00"},{"alias_kind":"pith_short_8","alias_value":"JD3F7SA7","created_at":"2026-07-05T01:16:41.748822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22610","citing_title":"PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10716","citing_title":"Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02606","citing_title":"ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03919","citing_title":"Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03864","citing_title":"Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08950","citing_title":"When More Cores Hurts: The Vector Database Scaling Paradox in HPC","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":184,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14306","citing_title":"Towards Recursive Self-Evolving Agentic Literature Retrieval","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":207,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07530","citing_title":"The Shrinking Lifespan of LLMs in Science","ref_index":12,"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":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5","json":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5.json","graph_json":"https://pith.science/api/pith-number/JD3F7SA75BOY4QB26VLB6LAIY5/graph.json","events_json":"https://pith.science/api/pith-number/JD3F7SA75BOY4QB26VLB6LAIY5/events.json","paper":"https://pith.science/paper/JD3F7SA7"},"agent_actions":{"view_html":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5","download_json":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5.json","view_paper":"https://pith.science/paper/JD3F7SA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.02782&json=true","fetch_graph":"https://pith.science/api/pith-number/JD3F7SA75BOY4QB26VLB6LAIY5/graph.json","fetch_events":"https://pith.science/api/pith-number/JD3F7SA75BOY4QB26VLB6LAIY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5/action/storage_attestation","attest_author":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5/action/author_attestation","sign_citation":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5/action/citation_signature","submit_replication":"https://pith.science/pith/JD3F7SA75BOY4QB26VLB6LAIY5/action/replication_record"}},"created_at":"2026-07-05T01:16:41.748822+00:00","updated_at":"2026-07-05T01:16:41.748822+00:00"}