{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KQ3PRRP53XFODQFELHETHYYFUM","short_pith_number":"pith:KQ3PRRP5","schema_version":"1.0","canonical_sha256":"5436f8c5fdddcae1c0a459c933e305a31f3472d83bdb1f355121627af0c97125","source":{"kind":"arxiv","id":"2302.08091","version":1},"attestation_state":"computed","paper":{"title":"Do We Still Need Clinical Language Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alistair Johnson, Daniel Nadler, Diwakar Mahajan, Emily Alsentzer, Eric Lehman, Evan Hernandez, Jonas Wulff, Micah J. Smith, Peter Szolovits, Zachary Ziegler","submitted_at":"2023-02-16T05:08:34Z","abstract_excerpt":"Although recent advances in scaling large language models (LLMs) have resulted in improvements on many NLP tasks, it remains unclear whether these models trained primarily with general web text are the right tool in highly specialized, safety critical domains such as clinical text. Recent results have suggested that LLMs encode a surprising amount of medical knowledge. This raises an important question regarding the utility of smaller domain-specific language models. With the success of general-domain LLMs, is there still a need for specialized clinical models? To investigate this question, we"},"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":"2302.08091","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-16T05:08:34Z","cross_cats_sorted":[],"title_canon_sha256":"7dca3ce6b277e1c15af9d3467c474a51ebbdd28e4e3cf8fe0e0b267ebb160bb0","abstract_canon_sha256":"7851fce04b78a28510134680592cc4d60612eb47da686a2b70e4d4c545b27546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:34.233100Z","signature_b64":"St7NRazAl963mGLdj2PsD8ANaIaQBEZ+O+QALTtdYkfm80sO85L4Uwv1ZkDPJy7uZUgaEPV99nPJ2ckw7O0cAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5436f8c5fdddcae1c0a459c933e305a31f3472d83bdb1f355121627af0c97125","last_reissued_at":"2026-07-05T05:42:34.232669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:34.232669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do We Still Need Clinical Language Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alistair Johnson, Daniel Nadler, Diwakar Mahajan, Emily Alsentzer, Eric Lehman, Evan Hernandez, Jonas Wulff, Micah J. Smith, Peter Szolovits, Zachary Ziegler","submitted_at":"2023-02-16T05:08:34Z","abstract_excerpt":"Although recent advances in scaling large language models (LLMs) have resulted in improvements on many NLP tasks, it remains unclear whether these models trained primarily with general web text are the right tool in highly specialized, safety critical domains such as clinical text. Recent results have suggested that LLMs encode a surprising amount of medical knowledge. This raises an important question regarding the utility of smaller domain-specific language models. With the success of general-domain LLMs, is there still a need for specialized clinical models? To investigate this question, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08091","kind":"arxiv","version":1},"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/2302.08091/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":"2302.08091","created_at":"2026-07-05T05:42:34.232724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.08091v1","created_at":"2026-07-05T05:42:34.232724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08091","created_at":"2026-07-05T05:42:34.232724+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQ3PRRP53XFO","created_at":"2026-07-05T05:42:34.232724+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQ3PRRP53XFODQFE","created_at":"2026-07-05T05:42:34.232724+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQ3PRRP5","created_at":"2026-07-05T05:42:34.232724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.09617","citing_title":"Towards Expert-Level Medical Question Answering with Large Language Models","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2303.17564","citing_title":"BloombergGPT: A Large Language Model for Finance","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18864","citing_title":"Towards an AI co-scientist","ref_index":194,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07116","citing_title":"Yale-DM-Lab at ArchEHR-QA 2026: Deterministic Grounding and Multi-Pass Evidence Alignment for EHR Question Answering","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM","json":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM.json","graph_json":"https://pith.science/api/pith-number/KQ3PRRP53XFODQFELHETHYYFUM/graph.json","events_json":"https://pith.science/api/pith-number/KQ3PRRP53XFODQFELHETHYYFUM/events.json","paper":"https://pith.science/paper/KQ3PRRP5"},"agent_actions":{"view_html":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM","download_json":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM.json","view_paper":"https://pith.science/paper/KQ3PRRP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.08091&json=true","fetch_graph":"https://pith.science/api/pith-number/KQ3PRRP53XFODQFELHETHYYFUM/graph.json","fetch_events":"https://pith.science/api/pith-number/KQ3PRRP53XFODQFELHETHYYFUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM/action/storage_attestation","attest_author":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM/action/author_attestation","sign_citation":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM/action/citation_signature","submit_replication":"https://pith.science/pith/KQ3PRRP53XFODQFELHETHYYFUM/action/replication_record"}},"created_at":"2026-07-05T05:42:34.232724+00:00","updated_at":"2026-07-05T05:42:34.232724+00:00"}