{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4LGZ2JMI7NFYVN74ZPXB2HC5UZ","short_pith_number":"pith:4LGZ2JMI","schema_version":"1.0","canonical_sha256":"e2cd9d2588fb4b8ab7fccbee1d1c5da674a4bfbb672d1bd520b80caf21691a0b","source":{"kind":"arxiv","id":"2203.03540","version":3},"attestation_state":"computed","paper":{"title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aokun Chen, Cheryl Martin, Christopher A Harle, Christopher Parisien, Colin Compas, Duane A Mitchell, Elizabeth A Shenkman, Gloria Lipori, Hoo Chang Shin, Jiang Bian, Kaleb E Smith, Mona G Flores, Nima PourNejatian, Tanja Magoc, William R Hogan, Xi Yang, Ying Zhang, Yonghui Wu","submitted_at":"2022-02-02T14:28:51Z","abstract_excerpt":"There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI"},"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":"2203.03540","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-02T14:28:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"51712b0f22ac0caf3e419e9fb9bc2aaab6be779c05fa7aa18621dd52073f78c1","abstract_canon_sha256":"e472cca3226c5c33a8d201d585c5ff044ed6d28a7d2b018944d460114be090f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:04.396106Z","signature_b64":"Wn9KOAHgGNBYU1rtXN+ueBOSUwnMjW+imHiegUigJRVzBnAr2UqnI2SvK2HB//DaMYHqqFkoMggjxgUUKFiHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2cd9d2588fb4b8ab7fccbee1d1c5da674a4bfbb672d1bd520b80caf21691a0b","last_reissued_at":"2026-07-05T05:26:04.395637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:04.395637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aokun Chen, Cheryl Martin, Christopher A Harle, Christopher Parisien, Colin Compas, Duane A Mitchell, Elizabeth A Shenkman, Gloria Lipori, Hoo Chang Shin, Jiang Bian, Kaleb E Smith, Mona G Flores, Nima PourNejatian, Tanja Magoc, William R Hogan, Xi Yang, Ying Zhang, Yonghui Wu","submitted_at":"2022-02-02T14:28:51Z","abstract_excerpt":"There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03540","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/2203.03540/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":"2203.03540","created_at":"2026-07-05T05:26:04.395698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.03540v3","created_at":"2026-07-05T05:26:04.395698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03540","created_at":"2026-07-05T05:26:04.395698+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LGZ2JMI7NFY","created_at":"2026-07-05T05:26:04.395698+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LGZ2JMI7NFYVN74","created_at":"2026-07-05T05:26:04.395698+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LGZ2JMI","created_at":"2026-07-05T05:26:04.395698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09125","citing_title":"Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28329","citing_title":"$M^3 QuestionIng$: Multi-modal Multi-span Medical Question Answering","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02501","citing_title":"ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ","json":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ.json","graph_json":"https://pith.science/api/pith-number/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/graph.json","events_json":"https://pith.science/api/pith-number/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/events.json","paper":"https://pith.science/paper/4LGZ2JMI"},"agent_actions":{"view_html":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ","download_json":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ.json","view_paper":"https://pith.science/paper/4LGZ2JMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.03540&json=true","fetch_graph":"https://pith.science/api/pith-number/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/action/storage_attestation","attest_author":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/action/author_attestation","sign_citation":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/action/citation_signature","submit_replication":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/action/replication_record"}},"created_at":"2026-07-05T05:26:04.395698+00:00","updated_at":"2026-07-05T05:26:04.395698+00:00"}