{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NA4IQGPN5LUL45H5EYO2AG5YKQ","short_pith_number":"pith:NA4IQGPN","schema_version":"1.0","canonical_sha256":"68388819edeae8be74fd261da01bb854258e20ada6a5c46c298cd187654ce6cc","source":{"kind":"arxiv","id":"2411.10020","version":4},"attestation_state":"computed","paper":{"title":"Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hua Xu, Jimin Huang, Kirk E. Roberts, Qingyu Chen, Ruey-Ling Weng, Vincent J. Zhang, Vipina K. Keloth, Xiaoqian Jiang, Xueqing Peng, Xu Zuo, Yan Hu, Yujia Zhou","submitted_at":"2024-11-15T07:54:19Z","abstract_excerpt":"Backgrounds: Information extraction (IE) is critical in clinical natural language processing (NLP). While large language models (LLMs) excel on generative tasks, their performance on extractive tasks remains debated. Methods: We investigated Named Entity Recognition (NER) and Relation Extraction (RE) using 1,588 clinical notes from four sources (UT Physicians, MTSamples, MIMIC-III, and i2b2). We developed an annotated corpus covering 4 clinical entities and 16 modifiers, and compared instruction-tuned LLaMA-2 and LLaMA-3 against BERT in terms of performance, generalizability, computational res"},"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":"2411.10020","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T07:54:19Z","cross_cats_sorted":[],"title_canon_sha256":"c5d76f10e4d11aa8363971d484d5191e4bbeb3346dd3a25686865204ebcd1b18","abstract_canon_sha256":"e9acb86304b5f66d1dd18edcf60c8a65730a1c4e115cc298524a891413b6c7c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:48.821160Z","signature_b64":"dCAd6laL7NaHnaelBuuBBQ08pMnue0vIFpnuCOqpIi8gNF/zPWFBvE3/zrDsg02+l6fDJqV72gXcLbU84m1NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68388819edeae8be74fd261da01bb854258e20ada6a5c46c298cd187654ce6cc","last_reissued_at":"2026-07-05T09:57:48.820541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:48.820541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hua Xu, Jimin Huang, Kirk E. Roberts, Qingyu Chen, Ruey-Ling Weng, Vincent J. Zhang, Vipina K. Keloth, Xiaoqian Jiang, Xueqing Peng, Xu Zuo, Yan Hu, Yujia Zhou","submitted_at":"2024-11-15T07:54:19Z","abstract_excerpt":"Backgrounds: Information extraction (IE) is critical in clinical natural language processing (NLP). While large language models (LLMs) excel on generative tasks, their performance on extractive tasks remains debated. Methods: We investigated Named Entity Recognition (NER) and Relation Extraction (RE) using 1,588 clinical notes from four sources (UT Physicians, MTSamples, MIMIC-III, and i2b2). We developed an annotated corpus covering 4 clinical entities and 16 modifiers, and compared instruction-tuned LLaMA-2 and LLaMA-3 against BERT in terms of performance, generalizability, computational res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10020","kind":"arxiv","version":4},"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/2411.10020/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":"2411.10020","created_at":"2026-07-05T09:57:48.820619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10020v4","created_at":"2026-07-05T09:57:48.820619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10020","created_at":"2026-07-05T09:57:48.820619+00:00"},{"alias_kind":"pith_short_12","alias_value":"NA4IQGPN5LUL","created_at":"2026-07-05T09:57:48.820619+00:00"},{"alias_kind":"pith_short_16","alias_value":"NA4IQGPN5LUL45H5","created_at":"2026-07-05T09:57:48.820619+00:00"},{"alias_kind":"pith_short_8","alias_value":"NA4IQGPN","created_at":"2026-07-05T09:57:48.820619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.11067","citing_title":"A Large Language Model Based Pipeline for Review of Systems Entity Recognition from Clinical Notes","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17214","citing_title":"Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ","json":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ.json","graph_json":"https://pith.science/api/pith-number/NA4IQGPN5LUL45H5EYO2AG5YKQ/graph.json","events_json":"https://pith.science/api/pith-number/NA4IQGPN5LUL45H5EYO2AG5YKQ/events.json","paper":"https://pith.science/paper/NA4IQGPN"},"agent_actions":{"view_html":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ","download_json":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ.json","view_paper":"https://pith.science/paper/NA4IQGPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10020&json=true","fetch_graph":"https://pith.science/api/pith-number/NA4IQGPN5LUL45H5EYO2AG5YKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NA4IQGPN5LUL45H5EYO2AG5YKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ/action/storage_attestation","attest_author":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ/action/author_attestation","sign_citation":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ/action/citation_signature","submit_replication":"https://pith.science/pith/NA4IQGPN5LUL45H5EYO2AG5YKQ/action/replication_record"}},"created_at":"2026-07-05T09:57:48.820619+00:00","updated_at":"2026-07-05T09:57:48.820619+00:00"}