{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B3MWDN4GZRG2I5LX5B3AGNNKGL","short_pith_number":"pith:B3MWDN4G","schema_version":"1.0","canonical_sha256":"0ed961b786cc4da47577e8760335aa32d0ee860bde5293c4b0bf09f34de29885","source":{"kind":"arxiv","id":"2411.04118","version":2},"attestation_state":"computed","paper":{"title":"Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel P. Jeong, Michael Oberst, Saurabh Garg, Zachary C. Lipton","submitted_at":"2024-11-06T18:51:02Z","abstract_excerpt":"Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare seven public \"medical\" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all"},"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":"2411.04118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T18:51:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"34c62be9c7eaf2da4a561e57e8cb13bd82178caf04e894d05a82758b06e68fe3","abstract_canon_sha256":"c72a3f8c8cf094461f5a47753969506e3955929e0346ede1030c11a3a31c7e98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:57.853089Z","signature_b64":"FQ9BH0qlBAjdpJuCOxzxKlpXcn5CYCp/OC1C/ehVMIyNZ7tvqoQCf12T6h6nRFPL6T9idk/GzK7j1DukKJPkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ed961b786cc4da47577e8760335aa32d0ee860bde5293c4b0bf09f34de29885","last_reissued_at":"2026-07-05T09:37:57.852608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:57.852608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel P. Jeong, Michael Oberst, Saurabh Garg, Zachary C. Lipton","submitted_at":"2024-11-06T18:51:02Z","abstract_excerpt":"Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare seven public \"medical\" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04118","kind":"arxiv","version":2},"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/2411.04118/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":"2411.04118","created_at":"2026-07-05T09:37:57.852665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04118v2","created_at":"2026-07-05T09:37:57.852665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04118","created_at":"2026-07-05T09:37:57.852665+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3MWDN4GZRG2","created_at":"2026-07-05T09:37:57.852665+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3MWDN4GZRG2I5LX","created_at":"2026-07-05T09:37:57.852665+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3MWDN4G","created_at":"2026-07-05T09:37:57.852665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02870","citing_title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","ref_index":216,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL","json":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL.json","graph_json":"https://pith.science/api/pith-number/B3MWDN4GZRG2I5LX5B3AGNNKGL/graph.json","events_json":"https://pith.science/api/pith-number/B3MWDN4GZRG2I5LX5B3AGNNKGL/events.json","paper":"https://pith.science/paper/B3MWDN4G"},"agent_actions":{"view_html":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL","download_json":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL.json","view_paper":"https://pith.science/paper/B3MWDN4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04118&json=true","fetch_graph":"https://pith.science/api/pith-number/B3MWDN4GZRG2I5LX5B3AGNNKGL/graph.json","fetch_events":"https://pith.science/api/pith-number/B3MWDN4GZRG2I5LX5B3AGNNKGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL/action/storage_attestation","attest_author":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL/action/author_attestation","sign_citation":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL/action/citation_signature","submit_replication":"https://pith.science/pith/B3MWDN4GZRG2I5LX5B3AGNNKGL/action/replication_record"}},"created_at":"2026-07-05T09:37:57.852665+00:00","updated_at":"2026-07-05T09:37:57.852665+00:00"}