{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BW4TTIXFTNA3GYWIYFHIDES73O","short_pith_number":"pith:BW4TTIXF","schema_version":"1.0","canonical_sha256":"0db939a2e59b41b362c8c14e81925fdbab6d6e032eceb33d82ec9e97cbb11a85","source":{"kind":"arxiv","id":"2310.14558","version":6},"attestation_state":"computed","paper":{"title":"AlpaCare:Instruction-tuned Large Language Models for Medical Application","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenxin Tian, Lichang Chen, Linda Ruth Petzold, Xianjun Yang, Xinlu Zhang, Zekun Li","submitted_at":"2023-10-23T04:22:50Z","abstract_excerpt":"Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications. However, previous studies mainly fine-tune LLMs on biomedical datasets with limited diversity, which often rely on benchmarks or narrow task scopes, and hence significantly limit the effectiveness on their medical instruction-following ability and generalizability. To bridge this gap, we propose creating a diverse, machine-generated medical IFT dataset, MedInstruct-52k, using GPT-4 and ChatGPT with a high-quality expert-curated"},"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":"2310.14558","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T04:22:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"990b3c4d696eccfee0b2614169b5a0bf6b05b735a0e105e445bdea436a209437","abstract_canon_sha256":"bd79d768bb4801704079efc21573c3e8c1b4917dc82cf4e1ffa03df59173dd1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:10.716104Z","signature_b64":"zg2foqQFJ1bbUB3I/D3bx72zCPSsNxthg3wqecFQq1qiCk3apHaPV6z3iGWKAAq6lxBMRspBEzLv46OcOTGeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0db939a2e59b41b362c8c14e81925fdbab6d6e032eceb33d82ec9e97cbb11a85","last_reissued_at":"2026-07-05T10:42:10.715621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:10.715621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AlpaCare:Instruction-tuned Large Language Models for Medical Application","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenxin Tian, Lichang Chen, Linda Ruth Petzold, Xianjun Yang, Xinlu Zhang, Zekun Li","submitted_at":"2023-10-23T04:22:50Z","abstract_excerpt":"Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications. However, previous studies mainly fine-tune LLMs on biomedical datasets with limited diversity, which often rely on benchmarks or narrow task scopes, and hence significantly limit the effectiveness on their medical instruction-following ability and generalizability. To bridge this gap, we propose creating a diverse, machine-generated medical IFT dataset, MedInstruct-52k, using GPT-4 and ChatGPT with a high-quality expert-curated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14558","kind":"arxiv","version":6},"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/2310.14558/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":"2310.14558","created_at":"2026-07-05T10:42:10.715679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14558v6","created_at":"2026-07-05T10:42:10.715679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14558","created_at":"2026-07-05T10:42:10.715679+00:00"},{"alias_kind":"pith_short_12","alias_value":"BW4TTIXFTNA3","created_at":"2026-07-05T10:42:10.715679+00:00"},{"alias_kind":"pith_short_16","alias_value":"BW4TTIXFTNA3GYWI","created_at":"2026-07-05T10:42:10.715679+00:00"},{"alias_kind":"pith_short_8","alias_value":"BW4TTIXF","created_at":"2026-07-05T10:42:10.715679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07853","citing_title":"Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25038","citing_title":"TRACE: A taxonomy-grounded synthetic dataset for teaching-program generation and session interpretation in Applied Behavior Analysis","ref_index":35,"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":73,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":237,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12516","citing_title":"Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01077","citing_title":"Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical Guidelines","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06154","citing_title":"Exclusive Unlearning","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O","json":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O.json","graph_json":"https://pith.science/api/pith-number/BW4TTIXFTNA3GYWIYFHIDES73O/graph.json","events_json":"https://pith.science/api/pith-number/BW4TTIXFTNA3GYWIYFHIDES73O/events.json","paper":"https://pith.science/paper/BW4TTIXF"},"agent_actions":{"view_html":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O","download_json":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O.json","view_paper":"https://pith.science/paper/BW4TTIXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14558&json=true","fetch_graph":"https://pith.science/api/pith-number/BW4TTIXFTNA3GYWIYFHIDES73O/graph.json","fetch_events":"https://pith.science/api/pith-number/BW4TTIXFTNA3GYWIYFHIDES73O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O/action/storage_attestation","attest_author":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O/action/author_attestation","sign_citation":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O/action/citation_signature","submit_replication":"https://pith.science/pith/BW4TTIXFTNA3GYWIYFHIDES73O/action/replication_record"}},"created_at":"2026-07-05T10:42:10.715679+00:00","updated_at":"2026-07-05T10:42:10.715679+00:00"}