{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4LGZ2JMI7NFYVN74ZPXB2HC5UZ","short_pith_number":"pith:4LGZ2JMI","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"},"canonical_sha256":"e2cd9d2588fb4b8ab7fccbee1d1c5da674a4bfbb672d1bd520b80caf21691a0b","source":{"kind":"arxiv","id":"2203.03540","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.03540","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2203.03540v3","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03540","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"4LGZ2JMI7NFY","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"4LGZ2JMI7NFYVN74","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"4LGZ2JMI","created_at":"2026-07-05T05:26:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4LGZ2JMI7NFYVN74ZPXB2HC5UZ","target":"record","payload":{"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"},"canonical_sha256":"e2cd9d2588fb4b8ab7fccbee1d1c5da674a4bfbb672d1bd520b80caf21691a0b","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"},"source_kind":"arxiv","source_id":"2203.03540","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wzIMEX71og0fMOCeJ9ke16N8qIjJargBhuWTuEdtUgD/ZoFewnEuMWIgAToAXGLwKrYK0kg3X4okE5oK7Fm3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:46:42.633755Z"},"content_sha256":"eaa26d0ee5a1ebe7c284a2de0e5ae67d169c4d7f1eb032f3332dfec591bc500f","schema_version":"1.0","event_id":"sha256:eaa26d0ee5a1ebe7c284a2de0e5ae67d169c4d7f1eb032f3332dfec591bc500f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4LGZ2JMI7NFYVN74ZPXB2HC5UZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wImmTrdts6UURGhwr9DPXgOR6x4Qdo2ThguH4CD2FToEPU8ZbraggbjXzXoGSOWFDYL31oxCc0ogSPjPgIZ+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:46:42.634149Z"},"content_sha256":"87ea2b02aa97450f27475e30a29eed44e940e6dcc2614496373162b98ccb2f2a","schema_version":"1.0","event_id":"sha256:87ea2b02aa97450f27475e30a29eed44e940e6dcc2614496373162b98ccb2f2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/bundle.json","state_url":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T13:46:42Z","links":{"resolver":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ","bundle":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/bundle.json","state":"https://pith.science/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4LGZ2JMI7NFYVN74ZPXB2HC5UZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4LGZ2JMI7NFYVN74ZPXB2HC5UZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e472cca3226c5c33a8d201d585c5ff044ed6d28a7d2b018944d460114be090f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-02T14:28:51Z","title_canon_sha256":"51712b0f22ac0caf3e419e9fb9bc2aaab6be779c05fa7aa18621dd52073f78c1"},"schema_version":"1.0","source":{"id":"2203.03540","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.03540","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2203.03540v3","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03540","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"4LGZ2JMI7NFY","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"4LGZ2JMI7NFYVN74","created_at":"2026-07-05T05:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"4LGZ2JMI","created_at":"2026-07-05T05:26:04Z"}],"graph_snapshots":[{"event_id":"sha256:87ea2b02aa97450f27475e30a29eed44e940e6dcc2614496373162b98ccb2f2a","target":"graph","created_at":"2026-07-05T05:26:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.03540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-02T14:28:51Z","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03540","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eaa26d0ee5a1ebe7c284a2de0e5ae67d169c4d7f1eb032f3332dfec591bc500f","target":"record","created_at":"2026-07-05T05:26:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e472cca3226c5c33a8d201d585c5ff044ed6d28a7d2b018944d460114be090f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-02T14:28:51Z","title_canon_sha256":"51712b0f22ac0caf3e419e9fb9bc2aaab6be779c05fa7aa18621dd52073f78c1"},"schema_version":"1.0","source":{"id":"2203.03540","kind":"arxiv","version":3}},"canonical_sha256":"e2cd9d2588fb4b8ab7fccbee1d1c5da674a4bfbb672d1bd520b80caf21691a0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2cd9d2588fb4b8ab7fccbee1d1c5da674a4bfbb672d1bd520b80caf21691a0b","first_computed_at":"2026-07-05T05:26:04.395637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:04.395637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wn9KOAHgGNBYU1rtXN+ueBOSUwnMjW+imHiegUigJRVzBnAr2UqnI2SvK2HB//DaMYHqqFkoMggjxgUUKFiHCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:04.396106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.03540","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaa26d0ee5a1ebe7c284a2de0e5ae67d169c4d7f1eb032f3332dfec591bc500f","sha256:87ea2b02aa97450f27475e30a29eed44e940e6dcc2614496373162b98ccb2f2a"],"state_sha256":"9abaac3c259577d0ae9834b0d94bed1893173e88cb0d423ac23aeeb3fd882c00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cQgffE/ZXFJlmA1ViIVrdK0fjBzsufAWtSkTBqP0I4ZX6t1ExUmj7dsStlZ0auMm2t+/TGx1/iuPjv6Hc8MIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T13:46:42.636461Z","bundle_sha256":"670b022d774ab8de4ec2402d6bbffa0e91948066b8461c53fd8a2c8c2cd07c73"}}