{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RJTES52YEG2OBCEPPFBCTM7VYC","short_pith_number":"pith:RJTES52Y","schema_version":"1.0","canonical_sha256":"8a6649775821b4e0888f794229b3f5c092b02092171e523d56bfb6ad389f9d7a","source":{"kind":"arxiv","id":"2311.16079","version":1},"attestation_state":"computed","paper":{"title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alejandro Hern\\'andez Cano, Alexandre Sallinen, Alireza Sakhaeirad, Amirkeivan Mohtashami, Andreas K\\\"opf, Angelika Romanou, Antoine Bonnet, Antoine Bosselut, Axel Marmet, Deniz Bayazit, Francesco Salvi, Igor Krawczuk, Kyle Matoba, Martin Jaggi, Mary-Anne Hartley, Matteo Pagliardini, Simin Fan, Syrielle Montariol, Vinitra Swamy, Zeming Chen","submitted_at":"2023-11-27T18:49:43Z","abstract_excerpt":"Large language models (LLMs) can potentially democratize access to medical knowledge. While many efforts have been made to harness and improve LLMs' medical knowledge and reasoning capacities, the resulting models are either closed-source (e.g., PaLM, GPT-4) or limited in scale (<= 13B parameters), which restricts their abilities. In this work, we improve access to large-scale medical LLMs by releasing MEDITRON: a suite of open-source LLMs with 7B and 70B parameters adapted to the medical domain. MEDITRON builds on Llama-2 (through our adaptation of Nvidia's Megatron-LM distributed trainer), a"},"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":"2311.16079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T18:49:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"879ec6e2422b1e0389609a890f0956a92b8b9899d9388e45b608e7a0c34e4aba","abstract_canon_sha256":"0e9f34087e9c1ddd238f6694cfc04a71275f4bbb5611a1769746fec4d0093109"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T14:02:22.838377Z","signature_b64":"klc3sSU1s4i/zcSXrYGFBrWqm1rifk3ZZcgDlRL8z7lsJV1vYHCc+I/VcGYrdmmLzJxadNMEFYH5kM5APhp/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a6649775821b4e0888f794229b3f5c092b02092171e523d56bfb6ad389f9d7a","last_reissued_at":"2026-05-21T14:02:22.835422Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T14:02:22.835422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alejandro Hern\\'andez Cano, Alexandre Sallinen, Alireza Sakhaeirad, Amirkeivan Mohtashami, Andreas K\\\"opf, Angelika Romanou, Antoine Bonnet, Antoine Bosselut, Axel Marmet, Deniz Bayazit, Francesco Salvi, Igor Krawczuk, Kyle Matoba, Martin Jaggi, Mary-Anne Hartley, Matteo Pagliardini, Simin Fan, Syrielle Montariol, Vinitra Swamy, Zeming Chen","submitted_at":"2023-11-27T18:49:43Z","abstract_excerpt":"Large language models (LLMs) can potentially democratize access to medical knowledge. While many efforts have been made to harness and improve LLMs' medical knowledge and reasoning capacities, the resulting models are either closed-source (e.g., PaLM, GPT-4) or limited in scale (<= 13B parameters), which restricts their abilities. In this work, we improve access to large-scale medical LLMs by releasing MEDITRON: a suite of open-source LLMs with 7B and 70B parameters adapted to the medical domain. MEDITRON builds on Llama-2 (through our adaptation of Nvidia's Megatron-LM distributed trainer), a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16079","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/2311.16079/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":"2311.16079","created_at":"2026-05-21T14:02:22.835549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16079v1","created_at":"2026-05-21T14:02:22.835549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16079","created_at":"2026-05-21T14:02:22.835549+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJTES52YEG2O","created_at":"2026-05-21T14:02:22.835549+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJTES52YEG2OBCEP","created_at":"2026-05-21T14:02:22.835549+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJTES52Y","created_at":"2026-05-21T14:02:22.835549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2405.07960","citing_title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15104","citing_title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15589","citing_title":"MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16215","citing_title":"Fully Open Meditron: An Auditable Pipeline for Clinical LLMs","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17379","citing_title":"Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26100","citing_title":"AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2601.13262","citing_title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2603.08022","citing_title":"Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16343","citing_title":"Elder-Sim: A Psychometrically Validated Platform for Personality-Stable Elderly Digital Twins","ref_index":36,"is_internal_anchor":true},{"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":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03216","citing_title":"BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11416","citing_title":"Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03476","citing_title":"CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27724","citing_title":"Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10025","citing_title":"Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25374","citing_title":"Language corpora for the Dutch medical domain","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00421","citing_title":"RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06903","citing_title":"Is Biomedical Specialization Still Worth It? Insights from Domain-Adaptive Language Modelling with a New French Health Corpus","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18753","citing_title":"Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC","json":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC.json","graph_json":"https://pith.science/api/pith-number/RJTES52YEG2OBCEPPFBCTM7VYC/graph.json","events_json":"https://pith.science/api/pith-number/RJTES52YEG2OBCEPPFBCTM7VYC/events.json","paper":"https://pith.science/paper/RJTES52Y"},"agent_actions":{"view_html":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC","download_json":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC.json","view_paper":"https://pith.science/paper/RJTES52Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16079&json=true","fetch_graph":"https://pith.science/api/pith-number/RJTES52YEG2OBCEPPFBCTM7VYC/graph.json","fetch_events":"https://pith.science/api/pith-number/RJTES52YEG2OBCEPPFBCTM7VYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC/action/storage_attestation","attest_author":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC/action/author_attestation","sign_citation":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC/action/citation_signature","submit_replication":"https://pith.science/pith/RJTES52YEG2OBCEPPFBCTM7VYC/action/replication_record"}},"created_at":"2026-05-21T14:02:22.835549+00:00","updated_at":"2026-05-21T14:02:22.835549+00:00"}