{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I44QJEUVPM6MMEFP5ZNSUNQV32","short_pith_number":"pith:I44QJEUV","schema_version":"1.0","canonical_sha256":"47390492957b3cc610afee5b2a3615de9171a5e601f19bc1db559e1471a31dcb","source":{"kind":"arxiv","id":"2504.04385","version":1},"attestation_state":"computed","paper":{"title":"Pre-trained Language Models and Few-shot Learning for Medical Entity Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binrong Zhu, Guiran Liu, Hanlu Zhang, Hongye Zheng, Jacky He, Xiaokai Wang","submitted_at":"2025-04-06T06:36:33Z","abstract_excerpt":"This study proposes a medical entity extraction method based on Transformer to enhance the information extraction capability of medical literature. Considering the professionalism and complexity of medical texts, we compare the performance of different pre-trained language models (BERT, BioBERT, PubMedBERT, ClinicalBERT) in medical entity extraction tasks. Experimental results show that PubMedBERT achieves the best performance (F1-score = 88.8%), indicating that a language model pre-trained on biomedical literature is more effective in the medical domain. In addition, we analyze the impact of "},"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":"2504.04385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-06T06:36:33Z","cross_cats_sorted":[],"title_canon_sha256":"86af8a12dd750bec241fb8380a85e883b54a350a38f76197c0ec925c332fa0a9","abstract_canon_sha256":"a7770f23d2dafb03b81edd77e048d8be3040cb30f7f506877e90e197d4cd7272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:22.957270Z","signature_b64":"ofkDOdeFni4NeI/7I6qG59RQ08MYVHmf6zHCglTQa6BB2qRfa40iwrMmCAfHHrCZ9xBEzXK6xbi6ve0S2Cb0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47390492957b3cc610afee5b2a3615de9171a5e601f19bc1db559e1471a31dcb","last_reissued_at":"2026-07-05T10:45:22.956807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:22.956807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-trained Language Models and Few-shot Learning for Medical Entity Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binrong Zhu, Guiran Liu, Hanlu Zhang, Hongye Zheng, Jacky He, Xiaokai Wang","submitted_at":"2025-04-06T06:36:33Z","abstract_excerpt":"This study proposes a medical entity extraction method based on Transformer to enhance the information extraction capability of medical literature. Considering the professionalism and complexity of medical texts, we compare the performance of different pre-trained language models (BERT, BioBERT, PubMedBERT, ClinicalBERT) in medical entity extraction tasks. Experimental results show that PubMedBERT achieves the best performance (F1-score = 88.8%), indicating that a language model pre-trained on biomedical literature is more effective in the medical domain. In addition, we analyze the impact of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04385","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/2504.04385/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":"2504.04385","created_at":"2026-07-05T10:45:22.956865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04385v1","created_at":"2026-07-05T10:45:22.956865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04385","created_at":"2026-07-05T10:45:22.956865+00:00"},{"alias_kind":"pith_short_12","alias_value":"I44QJEUVPM6M","created_at":"2026-07-05T10:45:22.956865+00:00"},{"alias_kind":"pith_short_16","alias_value":"I44QJEUVPM6MMEFP","created_at":"2026-07-05T10:45:22.956865+00:00"},{"alias_kind":"pith_short_8","alias_value":"I44QJEUV","created_at":"2026-07-05T10:45:22.956865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01437","citing_title":"Clinical NLP with Attention-Based Deep Learning for Multi-Disease Prediction","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32","json":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32.json","graph_json":"https://pith.science/api/pith-number/I44QJEUVPM6MMEFP5ZNSUNQV32/graph.json","events_json":"https://pith.science/api/pith-number/I44QJEUVPM6MMEFP5ZNSUNQV32/events.json","paper":"https://pith.science/paper/I44QJEUV"},"agent_actions":{"view_html":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32","download_json":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32.json","view_paper":"https://pith.science/paper/I44QJEUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04385&json=true","fetch_graph":"https://pith.science/api/pith-number/I44QJEUVPM6MMEFP5ZNSUNQV32/graph.json","fetch_events":"https://pith.science/api/pith-number/I44QJEUVPM6MMEFP5ZNSUNQV32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32/action/storage_attestation","attest_author":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32/action/author_attestation","sign_citation":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32/action/citation_signature","submit_replication":"https://pith.science/pith/I44QJEUVPM6MMEFP5ZNSUNQV32/action/replication_record"}},"created_at":"2026-07-05T10:45:22.956865+00:00","updated_at":"2026-07-05T10:45:22.956865+00:00"}