{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L37KPPPFS6R7SEG24MMTMVCLTP","short_pith_number":"pith:L37KPPPF","schema_version":"1.0","canonical_sha256":"5efea7bde597a3f910dae31936544b9bf8ed5947b5b68334194cf5ddefec0a10","source":{"kind":"arxiv","id":"2408.06142","version":1},"attestation_state":"computed","paper":{"title":"Med42-v2: A Suite of Clinical LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cl\\'ement Christophe, Marco AF Pimentel, Praveen K Kanithi, Shadab Khan, Tathagata Raha","submitted_at":"2024-08-12T13:37:31Z","abstract_excerpt":"Med42-v2 introduces a suite of clinical large language models (LLMs) designed to address the limitations of generic models in healthcare settings. These models are built on Llama3 architecture and fine-tuned using specialized clinical data. They underwent multi-stage preference alignment to effectively respond to natural prompts. While generic models are often preference-aligned to avoid answering clinical queries as a precaution, Med42-v2 is specifically trained to overcome this limitation, enabling its use in clinical settings. Med42-v2 models demonstrate superior performance compared to the"},"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":"2408.06142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-12T13:37:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f59203d3055b1cafa1d8aa8ef46ce65a1d1e90e76f761afb99c2a4978af0b6ae","abstract_canon_sha256":"014f1f0cb4bd96bb39e185554c66d96815761d6bf2ff29afcf6b74255f225fc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:30.191020Z","signature_b64":"x9ZcS66v4RhqWYZBRZdMq/YISbd6m/YPwaDlSARjrSQgiy0LmitnnPUd3jdnsZwJAlSrugCzxoH6wyCvQE3gAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5efea7bde597a3f910dae31936544b9bf8ed5947b5b68334194cf5ddefec0a10","last_reissued_at":"2026-07-05T08:54:30.190612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:30.190612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Med42-v2: A Suite of Clinical LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cl\\'ement Christophe, Marco AF Pimentel, Praveen K Kanithi, Shadab Khan, Tathagata Raha","submitted_at":"2024-08-12T13:37:31Z","abstract_excerpt":"Med42-v2 introduces a suite of clinical large language models (LLMs) designed to address the limitations of generic models in healthcare settings. These models are built on Llama3 architecture and fine-tuned using specialized clinical data. They underwent multi-stage preference alignment to effectively respond to natural prompts. While generic models are often preference-aligned to avoid answering clinical queries as a precaution, Med42-v2 is specifically trained to overcome this limitation, enabling its use in clinical settings. Med42-v2 models demonstrate superior performance compared to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06142","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/2408.06142/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":"2408.06142","created_at":"2026-07-05T08:54:30.190669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06142v1","created_at":"2026-07-05T08:54:30.190669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06142","created_at":"2026-07-05T08:54:30.190669+00:00"},{"alias_kind":"pith_short_12","alias_value":"L37KPPPFS6R7","created_at":"2026-07-05T08:54:30.190669+00:00"},{"alias_kind":"pith_short_16","alias_value":"L37KPPPFS6R7SEG2","created_at":"2026-07-05T08:54:30.190669+00:00"},{"alias_kind":"pith_short_8","alias_value":"L37KPPPF","created_at":"2026-07-05T08:54:30.190669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24901","citing_title":"LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12699","citing_title":"LLM-Powered Personalized Glycemic Assessment in Type 2 Diabetes with Wearable Sensor Data","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08071","citing_title":"SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03399","citing_title":"Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29034","citing_title":"The strength of clinical evidence is recoverable from language model representations but not from their stated grades","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27860","citing_title":"C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30637","citing_title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2502.07963","citing_title":"Caught in the Web of Words: Do LLMs Fall for Spin in Medical Literature?","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20537","citing_title":"What Do Biomedical NER and Entity Linking Benchmarks Measure? A Corpus-Centric Diagnostic Framework","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15589","citing_title":"MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08559","citing_title":"Medical Reasoning with Large Language Models: A Survey and MR-Bench","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02501","citing_title":"ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12313","citing_title":"Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05963","citing_title":"TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04882","citing_title":"FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05435","citing_title":"CareTransition-Audit: A Benchmark to Audit Discharge Summaries for Efficient Care Transitions","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP","json":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP.json","graph_json":"https://pith.science/api/pith-number/L37KPPPFS6R7SEG24MMTMVCLTP/graph.json","events_json":"https://pith.science/api/pith-number/L37KPPPFS6R7SEG24MMTMVCLTP/events.json","paper":"https://pith.science/paper/L37KPPPF"},"agent_actions":{"view_html":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP","download_json":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP.json","view_paper":"https://pith.science/paper/L37KPPPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06142&json=true","fetch_graph":"https://pith.science/api/pith-number/L37KPPPFS6R7SEG24MMTMVCLTP/graph.json","fetch_events":"https://pith.science/api/pith-number/L37KPPPFS6R7SEG24MMTMVCLTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP/action/storage_attestation","attest_author":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP/action/author_attestation","sign_citation":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP/action/citation_signature","submit_replication":"https://pith.science/pith/L37KPPPFS6R7SEG24MMTMVCLTP/action/replication_record"}},"created_at":"2026-07-05T08:54:30.190669+00:00","updated_at":"2026-07-05T08:54:30.190669+00:00"}