{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2WOGHSQAQUAN6P2GESGHMEKR72","short_pith_number":"pith:2WOGHSQA","schema_version":"1.0","canonical_sha256":"d59c63ca008500df3f46248c761151fe900081f5b71e4fb6a7886397e8c48595","source":{"kind":"arxiv","id":"2409.14988","version":1},"attestation_state":"computed","paper":{"title":"Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cl\\'ement Christophe, Marco AF Pimentel, Muhammad Umar Salman, Praveen K Kanithi, Shadab Khan, Svetlana Maslenkova, Tathagata Raha","submitted_at":"2024-09-23T13:09:57Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant potential in transforming clinical applications. In this study, we investigate the efficacy of four techniques in adapting LLMs for clinical use-cases: continuous pretraining, instruct fine-tuning, NEFTune, and prompt engineering. We employ these methods on Mistral 7B and Mixtral 8x7B models, leveraging a large-scale clinical pretraining dataset of 50 billion tokens and an instruct fine-tuning dataset of 500 million tokens. Our evaluation across various clinical tasks reveals the impact of each technique. While continuous pretraining b"},"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":"2409.14988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T13:09:57Z","cross_cats_sorted":[],"title_canon_sha256":"0cf1514e212496ba71fc8119306a1792fdc903741b54f671802b335c04ac6bce","abstract_canon_sha256":"1e202240665aadd89f12417ba094fe74d896a307abc692248ed86cec511ccccc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:34.382472Z","signature_b64":"NTsRHpF+95V1UbRXNAQ248WkfhzRAo6n9R7Wlk1x9gvzfoBVq+vnCFH3Eq+zXkhA21vpx55SdxNEvdpyv+MVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d59c63ca008500df3f46248c761151fe900081f5b71e4fb6a7886397e8c48595","last_reissued_at":"2026-07-05T09:10:34.382021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:34.382021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cl\\'ement Christophe, Marco AF Pimentel, Muhammad Umar Salman, Praveen K Kanithi, Shadab Khan, Svetlana Maslenkova, Tathagata Raha","submitted_at":"2024-09-23T13:09:57Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant potential in transforming clinical applications. In this study, we investigate the efficacy of four techniques in adapting LLMs for clinical use-cases: continuous pretraining, instruct fine-tuning, NEFTune, and prompt engineering. We employ these methods on Mistral 7B and Mixtral 8x7B models, leveraging a large-scale clinical pretraining dataset of 50 billion tokens and an instruct fine-tuning dataset of 500 million tokens. Our evaluation across various clinical tasks reveals the impact of each technique. While continuous pretraining b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14988","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/2409.14988/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":"2409.14988","created_at":"2026-07-05T09:10:34.382078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14988v1","created_at":"2026-07-05T09:10:34.382078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14988","created_at":"2026-07-05T09:10:34.382078+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WOGHSQAQUAN","created_at":"2026-07-05T09:10:34.382078+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WOGHSQAQUAN6P2G","created_at":"2026-07-05T09:10:34.382078+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WOGHSQA","created_at":"2026-07-05T09:10:34.382078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72","json":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72.json","graph_json":"https://pith.science/api/pith-number/2WOGHSQAQUAN6P2GESGHMEKR72/graph.json","events_json":"https://pith.science/api/pith-number/2WOGHSQAQUAN6P2GESGHMEKR72/events.json","paper":"https://pith.science/paper/2WOGHSQA"},"agent_actions":{"view_html":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72","download_json":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72.json","view_paper":"https://pith.science/paper/2WOGHSQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14988&json=true","fetch_graph":"https://pith.science/api/pith-number/2WOGHSQAQUAN6P2GESGHMEKR72/graph.json","fetch_events":"https://pith.science/api/pith-number/2WOGHSQAQUAN6P2GESGHMEKR72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/action/storage_attestation","attest_author":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/action/author_attestation","sign_citation":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/action/citation_signature","submit_replication":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/action/replication_record"}},"created_at":"2026-07-05T09:10:34.382078+00:00","updated_at":"2026-07-05T09:10:34.382078+00:00"}