{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2WOGHSQAQUAN6P2GESGHMEKR72","short_pith_number":"pith:2WOGHSQA","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"},"canonical_sha256":"d59c63ca008500df3f46248c761151fe900081f5b71e4fb6a7886397e8c48595","source":{"kind":"arxiv","id":"2409.14988","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14988","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14988v1","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14988","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"2WOGHSQAQUAN","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"2WOGHSQAQUAN6P2G","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"2WOGHSQA","created_at":"2026-07-05T09:10:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2WOGHSQAQUAN6P2GESGHMEKR72","target":"record","payload":{"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"},"canonical_sha256":"d59c63ca008500df3f46248c761151fe900081f5b71e4fb6a7886397e8c48595","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"},"source_kind":"arxiv","source_id":"2409.14988","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m5N3KqdDbOClFVHEF32n1HAa5yEhvum9IHi2gfP136BVZyubs/UALa0DunYoorPIJp+3z1EcUufGTRx3fzYhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:45:10.173557Z"},"content_sha256":"bf1ef214809269d834495f5af236fa965bfeea082d1930ce0adce119ff8436b4","schema_version":"1.0","event_id":"sha256:bf1ef214809269d834495f5af236fa965bfeea082d1930ce0adce119ff8436b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2WOGHSQAQUAN6P2GESGHMEKR72","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l5RRZkMLyDNWWMvYNbfwwZVjJPjPQ6hI1DBiwzi/y9VDjfIWEjj01Yv85/iFprNKJoXO2hRHCWNXMlSVlO8tBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:45:10.174233Z"},"content_sha256":"4f1ed4049baba1b69b8ef29a32487ac43173014a1ce0c7bae6210dd6ac02bb1c","schema_version":"1.0","event_id":"sha256:4f1ed4049baba1b69b8ef29a32487ac43173014a1ce0c7bae6210dd6ac02bb1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/bundle.json","state_url":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2WOGHSQAQUAN6P2GESGHMEKR72/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":"2026-08-04T13:45:10Z","links":{"resolver":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72","bundle":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/bundle.json","state":"https://pith.science/pith/2WOGHSQAQUAN6P2GESGHMEKR72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2WOGHSQAQUAN6P2GESGHMEKR72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2WOGHSQAQUAN6P2GESGHMEKR72","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":"1e202240665aadd89f12417ba094fe74d896a307abc692248ed86cec511ccccc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T13:09:57Z","title_canon_sha256":"0cf1514e212496ba71fc8119306a1792fdc903741b54f671802b335c04ac6bce"},"schema_version":"1.0","source":{"id":"2409.14988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14988","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14988v1","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14988","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"2WOGHSQAQUAN","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"2WOGHSQAQUAN6P2G","created_at":"2026-07-05T09:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"2WOGHSQA","created_at":"2026-07-05T09:10:34Z"}],"graph_snapshots":[{"event_id":"sha256:4f1ed4049baba1b69b8ef29a32487ac43173014a1ce0c7bae6210dd6ac02bb1c","target":"graph","created_at":"2026-07-05T09:10:34Z","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/2409.14988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cl\\'ement Christophe, Marco AF Pimentel, Muhammad Umar Salman, Praveen K Kanithi, Shadab Khan, Svetlana Maslenkova, Tathagata Raha","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T13:09:57Z","title":"Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14988","kind":"arxiv","version":1},"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:bf1ef214809269d834495f5af236fa965bfeea082d1930ce0adce119ff8436b4","target":"record","created_at":"2026-07-05T09:10:34Z","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":"1e202240665aadd89f12417ba094fe74d896a307abc692248ed86cec511ccccc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T13:09:57Z","title_canon_sha256":"0cf1514e212496ba71fc8119306a1792fdc903741b54f671802b335c04ac6bce"},"schema_version":"1.0","source":{"id":"2409.14988","kind":"arxiv","version":1}},"canonical_sha256":"d59c63ca008500df3f46248c761151fe900081f5b71e4fb6a7886397e8c48595","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d59c63ca008500df3f46248c761151fe900081f5b71e4fb6a7886397e8c48595","first_computed_at":"2026-07-05T09:10:34.382021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:34.382021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NTsRHpF+95V1UbRXNAQ248WkfhzRAo6n9R7Wlk1x9gvzfoBVq+vnCFH3Eq+zXkhA21vpx55SdxNEvdpyv+MVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:34.382472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf1ef214809269d834495f5af236fa965bfeea082d1930ce0adce119ff8436b4","sha256:4f1ed4049baba1b69b8ef29a32487ac43173014a1ce0c7bae6210dd6ac02bb1c"],"state_sha256":"fb1c224a48d81e2ff28af922287bbf181e77a4379dc6a78a29342c26aaa620b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8uwosB1jPPoWasUaWxrIUv0XIQim4y/EMnrGwqYkqzgjzU9QuX0940C7mO7fc1oRq+cKUGFeYJ+USDKQZPeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:45:10.179268Z","bundle_sha256":"98742cfc55305c2b8c0959b761f694457a8c053b52bd89989fd7cbf7f61818b7"}}