{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:INES2YPZ5DKHFTIM22PRSSFXVA","short_pith_number":"pith:INES2YPZ","schema_version":"1.0","canonical_sha256":"43492d61f9e8d472cd0cd69f1948b7a81f2a44df6e227bd03efd0a7e37be3afc","source":{"kind":"arxiv","id":"2501.00031","version":1},"attestation_state":"computed","paper":{"title":"Distilling Large Language Models for Efficient Clinical Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshay Swaminathan, Annika Gupta, Ivan Lopez, Karthik S. Vedula, Nigam H. Shah, Suhana Bedi","submitted_at":"2024-12-21T02:15:29Z","abstract_excerpt":"Large language models (LLMs) excel at clinical information extraction but their computational demands limit practical deployment. Knowledge distillation--the process of transferring knowledge from larger to smaller models--offers a potential solution. We evaluate the performance of distilled BERT models, which are approximately 1,000 times smaller than modern LLMs, for clinical named entity recognition (NER) tasks. We leveraged state-of-the-art LLMs (Gemini and OpenAI models) and medical ontologies (RxNorm and SNOMED) as teacher labelers for medication, disease, and symptom extraction. We appl"},"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":"2501.00031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T02:15:29Z","cross_cats_sorted":[],"title_canon_sha256":"28fe8f2ea80d4c490bbc7f5e245a2057b6ce82a6af8ef66e46f6bfa23bfb4058","abstract_canon_sha256":"c6fb4654b36f40baf26f995c3f99c5facfcb1dcce2158771895cab031bcb0ddc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:37.940111Z","signature_b64":"wrN+k6oawF7oH4A1eONHtHlNI+C5fQZjy/MiI2P9P5GhnXQPgpG6aaq/XDAO+AZdH9elUVQgr5JuX8NM/PKhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43492d61f9e8d472cd0cd69f1948b7a81f2a44df6e227bd03efd0a7e37be3afc","last_reissued_at":"2026-07-05T09:55:37.939755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:37.939755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Large Language Models for Efficient Clinical Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshay Swaminathan, Annika Gupta, Ivan Lopez, Karthik S. Vedula, Nigam H. Shah, Suhana Bedi","submitted_at":"2024-12-21T02:15:29Z","abstract_excerpt":"Large language models (LLMs) excel at clinical information extraction but their computational demands limit practical deployment. Knowledge distillation--the process of transferring knowledge from larger to smaller models--offers a potential solution. We evaluate the performance of distilled BERT models, which are approximately 1,000 times smaller than modern LLMs, for clinical named entity recognition (NER) tasks. We leveraged state-of-the-art LLMs (Gemini and OpenAI models) and medical ontologies (RxNorm and SNOMED) as teacher labelers for medication, disease, and symptom extraction. We appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00031","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/2501.00031/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":"2501.00031","created_at":"2026-07-05T09:55:37.939815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00031v1","created_at":"2026-07-05T09:55:37.939815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00031","created_at":"2026-07-05T09:55:37.939815+00:00"},{"alias_kind":"pith_short_12","alias_value":"INES2YPZ5DKH","created_at":"2026-07-05T09:55:37.939815+00:00"},{"alias_kind":"pith_short_16","alias_value":"INES2YPZ5DKHFTIM","created_at":"2026-07-05T09:55:37.939815+00:00"},{"alias_kind":"pith_short_8","alias_value":"INES2YPZ","created_at":"2026-07-05T09:55:37.939815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA","json":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA.json","graph_json":"https://pith.science/api/pith-number/INES2YPZ5DKHFTIM22PRSSFXVA/graph.json","events_json":"https://pith.science/api/pith-number/INES2YPZ5DKHFTIM22PRSSFXVA/events.json","paper":"https://pith.science/paper/INES2YPZ"},"agent_actions":{"view_html":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA","download_json":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA.json","view_paper":"https://pith.science/paper/INES2YPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00031&json=true","fetch_graph":"https://pith.science/api/pith-number/INES2YPZ5DKHFTIM22PRSSFXVA/graph.json","fetch_events":"https://pith.science/api/pith-number/INES2YPZ5DKHFTIM22PRSSFXVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/action/storage_attestation","attest_author":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/action/author_attestation","sign_citation":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/action/citation_signature","submit_replication":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/action/replication_record"}},"created_at":"2026-07-05T09:55:37.939815+00:00","updated_at":"2026-07-05T09:55:37.939815+00:00"}