{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VQCHQL7W6CYJLKP4QQ6RIUBBPL","short_pith_number":"pith:VQCHQL7W","schema_version":"1.0","canonical_sha256":"ac04782ff6f0b095a9fc843d1450217ad596d39292f193592611caf390ad8413","source":{"kind":"arxiv","id":"2402.10373","version":3},"attestation_state":"computed","paper":{"title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adrien Bazoge, Emmanuel Morin, Mickael Rouvier, Pierre-Antoine Gourraud, Richard Dufour, Yanis Labrak","submitted_at":"2024-02-15T23:39:04Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges. In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark compri"},"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":"2402.10373","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T23:39:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1d92d6b7a9715f5f1c7cc4d86a9aecdad10b647179e7c3bf4eb14febd5f627ef","abstract_canon_sha256":"9e816281256abeaca846227503c531da53ec879e25fc1075274422eb788de90f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:51.043102Z","signature_b64":"NpKDlK7NMcYBQJETUS/FTqP7UQZRRLWPp/mCRxm4uP5gf/94hAHMXmtHKwyJ14GAdq9U1SjgecGo06mp8lwRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac04782ff6f0b095a9fc843d1450217ad596d39292f193592611caf390ad8413","last_reissued_at":"2026-07-05T08:44:51.042657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:51.042657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adrien Bazoge, Emmanuel Morin, Mickael Rouvier, Pierre-Antoine Gourraud, Richard Dufour, Yanis Labrak","submitted_at":"2024-02-15T23:39:04Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. Despite the availability of various open-source LLMs tailored for health contexts, adapting general-purpose LLMs to the medical domain presents significant challenges. In this paper, we introduce BioMistral, an open-source LLM tailored for the biomedical domain, utilizing Mistral as its foundation model and further pre-trained on PubMed Central. We conduct a comprehensive evaluation of BioMistral on a benchmark compri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10373","kind":"arxiv","version":3},"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/2402.10373/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":"2402.10373","created_at":"2026-07-05T08:44:51.042714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10373v3","created_at":"2026-07-05T08:44:51.042714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10373","created_at":"2026-07-05T08:44:51.042714+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQCHQL7W6CYJ","created_at":"2026-07-05T08:44:51.042714+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQCHQL7W6CYJLKP4","created_at":"2026-07-05T08:44:51.042714+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQCHQL7W","created_at":"2026-07-05T08:44:51.042714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18752","citing_title":"A Scientific Human-Agent Reproduction Pipeline","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10796","citing_title":"Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09401","citing_title":"Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models","ref_index":289,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02802","citing_title":"ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31171","citing_title":"Cross-Domain Feature Expansion for Tabular Medical Data via Knowledge Graphs Injection","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29744","citing_title":"Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22402","citing_title":"Reinforcement learning to improve large language model-based automated code compliance systems","ref_index":38,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2502.16022","citing_title":"Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation: A Comparative Study","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24730","citing_title":"Diamonds in the rough: Transforming SPARCs of imagination into a game concept by leveraging medium sized LLMs","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15104","citing_title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16639","citing_title":"MedMIX: Modality-Internal Expert Fusion for Multimodal Medical Diagnosis","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19630","citing_title":"Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13262","citing_title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19776","citing_title":"Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa","ref_index":33,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00421","citing_title":"RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13021","citing_title":"Representation geometry shapes task performance in vision-language modeling for CT enterography","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10441","citing_title":"VeriSim: A Configurable Framework for Evaluating Medical AI Under Realistic Patient Noise","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06854","citing_title":"To Adapt or not to Adapt, Rethinking the Value of Medical Knowledge-Aware Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19815","citing_title":"Large Language Models Meet Biomedical Knowledge Graphs for Mechanistically Grounded Therapeutic Prioritization","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18753","citing_title":"Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21076","citing_title":"Serialisation Strategy Matters: How FHIR Data Format Affects LLM Medication Reconciliation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL","json":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL.json","graph_json":"https://pith.science/api/pith-number/VQCHQL7W6CYJLKP4QQ6RIUBBPL/graph.json","events_json":"https://pith.science/api/pith-number/VQCHQL7W6CYJLKP4QQ6RIUBBPL/events.json","paper":"https://pith.science/paper/VQCHQL7W"},"agent_actions":{"view_html":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL","download_json":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL.json","view_paper":"https://pith.science/paper/VQCHQL7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10373&json=true","fetch_graph":"https://pith.science/api/pith-number/VQCHQL7W6CYJLKP4QQ6RIUBBPL/graph.json","fetch_events":"https://pith.science/api/pith-number/VQCHQL7W6CYJLKP4QQ6RIUBBPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL/action/storage_attestation","attest_author":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL/action/author_attestation","sign_citation":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL/action/citation_signature","submit_replication":"https://pith.science/pith/VQCHQL7W6CYJLKP4QQ6RIUBBPL/action/replication_record"}},"created_at":"2026-07-05T08:44:51.042714+00:00","updated_at":"2026-07-05T08:44:51.042714+00:00"}