{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6LCE5ZYA7JFOOL34IUQCADQ73V","short_pith_number":"pith:6LCE5ZYA","schema_version":"1.0","canonical_sha256":"f2c44ee700fa4ae72f7c4520200e1fdd499fff98132cac33e213a937521eac34","source":{"kind":"arxiv","id":"2502.11861","version":1},"attestation_state":"computed","paper":{"title":"Exploring Large Language Models in Healthcare: Insights into Corpora Sources, Customization Strategies, and Evaluation Metrics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaxin Kou, Manfei Shi, Mingrui Jing, Shuai Wang, Shuqi Yang, Weijie Xing, Yan Hu, Zheng Zhu","submitted_at":"2025-02-17T14:53:23Z","abstract_excerpt":"This study reviewed the use of Large Language Models (LLMs) in healthcare, focusing on their training corpora, customization techniques, and evaluation metrics. A systematic search of studies from 2021 to 2024 identified 61 articles. Four types of corpora were used: clinical resources, literature, open-source datasets, and web-crawled data. Common construction techniques included pre-training, prompt engineering, and retrieval-augmented generation, with 44 studies combining multiple methods. Evaluation metrics were categorized into process, usability, and outcome metrics, with outcome metrics "},"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":"2502.11861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T14:53:23Z","cross_cats_sorted":[],"title_canon_sha256":"ef2f39a11e8bf9141260b1ad392baf9887841a6ddcb01132d44e9a48dd4dc290","abstract_canon_sha256":"6e97e7ad847c2607d427de26b079d8b1f4cf0e85a4741ebf1d827ed0a6c94a3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:35.354550Z","signature_b64":"kDFCVexTsE0WZo3W+q8kSOa9YWWU06OEpHY/MWUz2mk6niJMJSygVfo+zTsPJN7sJiKsYR5PCCoPUMiFjLlhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2c44ee700fa4ae72f7c4520200e1fdd499fff98132cac33e213a937521eac34","last_reissued_at":"2026-07-05T10:15:35.354060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:35.354060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Large Language Models in Healthcare: Insights into Corpora Sources, Customization Strategies, and Evaluation Metrics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaxin Kou, Manfei Shi, Mingrui Jing, Shuai Wang, Shuqi Yang, Weijie Xing, Yan Hu, Zheng Zhu","submitted_at":"2025-02-17T14:53:23Z","abstract_excerpt":"This study reviewed the use of Large Language Models (LLMs) in healthcare, focusing on their training corpora, customization techniques, and evaluation metrics. A systematic search of studies from 2021 to 2024 identified 61 articles. Four types of corpora were used: clinical resources, literature, open-source datasets, and web-crawled data. Common construction techniques included pre-training, prompt engineering, and retrieval-augmented generation, with 44 studies combining multiple methods. Evaluation metrics were categorized into process, usability, and outcome metrics, with outcome metrics "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11861","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/2502.11861/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":"2502.11861","created_at":"2026-07-05T10:15:35.354117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11861v1","created_at":"2026-07-05T10:15:35.354117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11861","created_at":"2026-07-05T10:15:35.354117+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LCE5ZYA7JFO","created_at":"2026-07-05T10:15:35.354117+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LCE5ZYA7JFOOL34","created_at":"2026-07-05T10:15:35.354117+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LCE5ZYA","created_at":"2026-07-05T10:15:35.354117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23806","citing_title":"MedOrchestra: A Hybrid Cloud-Local LLM Approach for Clinical Data Interpretation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V","json":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V.json","graph_json":"https://pith.science/api/pith-number/6LCE5ZYA7JFOOL34IUQCADQ73V/graph.json","events_json":"https://pith.science/api/pith-number/6LCE5ZYA7JFOOL34IUQCADQ73V/events.json","paper":"https://pith.science/paper/6LCE5ZYA"},"agent_actions":{"view_html":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V","download_json":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V.json","view_paper":"https://pith.science/paper/6LCE5ZYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11861&json=true","fetch_graph":"https://pith.science/api/pith-number/6LCE5ZYA7JFOOL34IUQCADQ73V/graph.json","fetch_events":"https://pith.science/api/pith-number/6LCE5ZYA7JFOOL34IUQCADQ73V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V/action/storage_attestation","attest_author":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V/action/author_attestation","sign_citation":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V/action/citation_signature","submit_replication":"https://pith.science/pith/6LCE5ZYA7JFOOL34IUQCADQ73V/action/replication_record"}},"created_at":"2026-07-05T10:15:35.354117+00:00","updated_at":"2026-07-05T10:15:35.354117+00:00"}