{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7Q73XVATD4FNP3YZHGNN4WAELU","short_pith_number":"pith:7Q73XVAT","schema_version":"1.0","canonical_sha256":"fc3fbbd4131f0ad7ef19399ade58045d2e1db4eff1171900fb2967c20e7d7ad0","source":{"kind":"arxiv","id":"2304.08247","version":3},"attestation_state":"computed","paper":{"title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander L\\\"oser, Alexei Figueroa, Daniel Truhn, Jens-Michalis Papaioannou, Keno K. Bressem, Lisa C. Adams, Paul Grundmann, Tianyu Han, Tom Oberhauser","submitted_at":"2023-04-14T11:28:08Z","abstract_excerpt":"As large language models (LLMs) like OpenAI's GPT series continue to make strides, we witness the emergence of artificial intelligence applications in an ever-expanding range of fields. In medicine, these LLMs hold considerable promise for improving medical workflows, diagnostics, patient care, and education. Yet, there is an urgent need for open-source models that can be deployed on-premises to safeguard patient privacy. In our work, we present an innovative dataset consisting of over 160,000 entries, specifically crafted to fine-tune LLMs for effective medical applications. We investigate th"},"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":"2304.08247","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-14T11:28:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90deaea3878c1a5bb54638b2420e4a0a5e09c812ea6d4d9b7e1c0b64d7806bf8","abstract_canon_sha256":"0978abcb0fa82fa853dcf5456a15fd1274ab2c58729d8a38d027724ea121e26c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:04.797433Z","signature_b64":"kcV55kkL1GPCKQ/ehAbcJaD50EY8A/UAEvVAi2oTa68zwx8onXbAtTP4OyxSBywUp5sFU93ZHJZHAfoJbqiACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc3fbbd4131f0ad7ef19399ade58045d2e1db4eff1171900fb2967c20e7d7ad0","last_reissued_at":"2026-07-05T10:34:04.796876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:04.796876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander L\\\"oser, Alexei Figueroa, Daniel Truhn, Jens-Michalis Papaioannou, Keno K. Bressem, Lisa C. Adams, Paul Grundmann, Tianyu Han, Tom Oberhauser","submitted_at":"2023-04-14T11:28:08Z","abstract_excerpt":"As large language models (LLMs) like OpenAI's GPT series continue to make strides, we witness the emergence of artificial intelligence applications in an ever-expanding range of fields. In medicine, these LLMs hold considerable promise for improving medical workflows, diagnostics, patient care, and education. Yet, there is an urgent need for open-source models that can be deployed on-premises to safeguard patient privacy. In our work, we present an innovative dataset consisting of over 160,000 entries, specifically crafted to fine-tune LLMs for effective medical applications. We investigate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08247","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/2304.08247/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":"2304.08247","created_at":"2026-07-05T10:34:04.796932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08247v3","created_at":"2026-07-05T10:34:04.796932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08247","created_at":"2026-07-05T10:34:04.796932+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q73XVATD4FN","created_at":"2026-07-05T10:34:04.796932+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q73XVATD4FNP3YZ","created_at":"2026-07-05T10:34:04.796932+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q73XVAT","created_at":"2026-07-05T10:34:04.796932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19364","citing_title":"Closing the Social-Semantic Gap: SPSD for Edge-Based Prompt Compression in Cloud LLM Inference","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04262","citing_title":"Can I Take Another Dose? Evaluating LLM Decision-Making Under Temporal Uncertainty in OTC Dosing QA","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26567","citing_title":"MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01301","citing_title":"Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12805","citing_title":"SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2306.00890","citing_title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05640","citing_title":"FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20591","citing_title":"Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18028","citing_title":"FedSDR: Federated Self-Distillation with Rectification","ref_index":59,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03525","citing_title":"Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13262","citing_title":"CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21577","citing_title":"Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06180","citing_title":"MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":51,"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":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19060","citing_title":"Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports","ref_index":16,"is_internal_anchor":false},{"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":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU","json":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU.json","graph_json":"https://pith.science/api/pith-number/7Q73XVATD4FNP3YZHGNN4WAELU/graph.json","events_json":"https://pith.science/api/pith-number/7Q73XVATD4FNP3YZHGNN4WAELU/events.json","paper":"https://pith.science/paper/7Q73XVAT"},"agent_actions":{"view_html":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU","download_json":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU.json","view_paper":"https://pith.science/paper/7Q73XVAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08247&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q73XVATD4FNP3YZHGNN4WAELU/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q73XVATD4FNP3YZHGNN4WAELU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU/action/storage_attestation","attest_author":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU/action/author_attestation","sign_citation":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU/action/citation_signature","submit_replication":"https://pith.science/pith/7Q73XVATD4FNP3YZHGNN4WAELU/action/replication_record"}},"created_at":"2026-07-05T10:34:04.796932+00:00","updated_at":"2026-07-05T10:34:04.796932+00:00"}