{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DUKSCABAKF4XHZLZZRIJVGWASZ","short_pith_number":"pith:DUKSCABA","schema_version":"1.0","canonical_sha256":"1d15210020517973e579cc509a9ac09644a78c84dc463c789273c8ad36871d1c","source":{"kind":"arxiv","id":"1902.07669","version":3},"attestation_state":"computed","paper":{"title":"ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel King, Iz Beltagy, Mark Neumann, Waleed Ammar","submitted_at":"2019-02-20T17:28:51Z","abstract_excerpt":"Despite recent advances in natural language processing, many statistical models for processing text perform extremely poorly under domain shift. Processing biomedical and clinical text is a critically important application area of natural language processing, for which there are few robust, practical, publicly available models. This paper describes scispaCy, a new tool for practical biomedical/scientific text processing, which heavily leverages the spaCy library. We detail the performance of two packages of models released in scispaCy and demonstrate their robustness on several tasks and datas"},"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":"1902.07669","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-02-20T17:28:51Z","cross_cats_sorted":[],"title_canon_sha256":"c2f62ce56def404daff5b0c1d820c87abb82073326e2df4b62d7b59c93acdf90","abstract_canon_sha256":"55ddd9ff6a7e59d1b72660f3146d60660ffdce771ba007dbcacb076f8b224548"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:15.661759Z","signature_b64":"RGCbgVkg9rzmxYGl9F+vlZhjq+uHWJoOx6ZEKMAZA364VgCdq3X1A93NS+h9kngUxvFmSy3iFJ3LL0gtvjSnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d15210020517973e579cc509a9ac09644a78c84dc463c789273c8ad36871d1c","last_reissued_at":"2026-07-05T02:25:15.661257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:15.661257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel King, Iz Beltagy, Mark Neumann, Waleed Ammar","submitted_at":"2019-02-20T17:28:51Z","abstract_excerpt":"Despite recent advances in natural language processing, many statistical models for processing text perform extremely poorly under domain shift. Processing biomedical and clinical text is a critically important application area of natural language processing, for which there are few robust, practical, publicly available models. This paper describes scispaCy, a new tool for practical biomedical/scientific text processing, which heavily leverages the spaCy library. We detail the performance of two packages of models released in scispaCy and demonstrate their robustness on several tasks and datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07669","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/1902.07669/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":"1902.07669","created_at":"2026-07-05T02:25:15.661320+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.07669v3","created_at":"2026-07-05T02:25:15.661320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07669","created_at":"2026-07-05T02:25:15.661320+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUKSCABAKF4X","created_at":"2026-07-05T02:25:15.661320+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUKSCABAKF4XHZLZ","created_at":"2026-07-05T02:25:15.661320+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUKSCABA","created_at":"2026-07-05T02:25:15.661320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.16022","citing_title":"Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation: A Comparative Study","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17114","citing_title":"The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ","json":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ.json","graph_json":"https://pith.science/api/pith-number/DUKSCABAKF4XHZLZZRIJVGWASZ/graph.json","events_json":"https://pith.science/api/pith-number/DUKSCABAKF4XHZLZZRIJVGWASZ/events.json","paper":"https://pith.science/paper/DUKSCABA"},"agent_actions":{"view_html":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ","download_json":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ.json","view_paper":"https://pith.science/paper/DUKSCABA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.07669&json=true","fetch_graph":"https://pith.science/api/pith-number/DUKSCABAKF4XHZLZZRIJVGWASZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DUKSCABAKF4XHZLZZRIJVGWASZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ/action/storage_attestation","attest_author":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ/action/author_attestation","sign_citation":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ/action/citation_signature","submit_replication":"https://pith.science/pith/DUKSCABAKF4XHZLZZRIJVGWASZ/action/replication_record"}},"created_at":"2026-07-05T02:25:15.661320+00:00","updated_at":"2026-07-05T02:25:15.661320+00:00"}