{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:INES2YPZ5DKHFTIM22PRSSFXVA","short_pith_number":"pith:INES2YPZ","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"},"canonical_sha256":"43492d61f9e8d472cd0cd69f1948b7a81f2a44df6e227bd03efd0a7e37be3afc","source":{"kind":"arxiv","id":"2501.00031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00031","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00031v1","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00031","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"INES2YPZ5DKH","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_16","alias_value":"INES2YPZ5DKHFTIM","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_8","alias_value":"INES2YPZ","created_at":"2026-07-05T09:55:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:INES2YPZ5DKHFTIM22PRSSFXVA","target":"record","payload":{"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"},"canonical_sha256":"43492d61f9e8d472cd0cd69f1948b7a81f2a44df6e227bd03efd0a7e37be3afc","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"},"source_kind":"arxiv","source_id":"2501.00031","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YY9S+/4KvjaS7sVEfuSm9lu/xFMmkVpyfnY/hgQz2BSMoTPmDkoGdsg2vNz9vxMhljJc85cX0QWMtBRTd9G/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:22:13.037040Z"},"content_sha256":"472e58d8bc34e3e6e0ee708f1567b65c9e3d8fe8e0b5463e4a9e4a01248b4c2f","schema_version":"1.0","event_id":"sha256:472e58d8bc34e3e6e0ee708f1567b65c9e3d8fe8e0b5463e4a9e4a01248b4c2f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:INES2YPZ5DKHFTIM22PRSSFXVA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8t4hOGr/mQmGWqzn7r7VTfBylS68Fh3jBanphNrmKmzBvE4d4Z8yI5RwbwKnV69zzt5pSjx1SVAXuH4zmQiVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:22:13.037419Z"},"content_sha256":"938b22dcccdf998ef5331afb67ea39380e7bc26920ffb9f99e7a53766eb6fa35","schema_version":"1.0","event_id":"sha256:938b22dcccdf998ef5331afb67ea39380e7bc26920ffb9f99e7a53766eb6fa35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/bundle.json","state_url":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/INES2YPZ5DKHFTIM22PRSSFXVA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T04:22:13Z","links":{"resolver":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA","bundle":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/bundle.json","state":"https://pith.science/pith/INES2YPZ5DKHFTIM22PRSSFXVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/INES2YPZ5DKHFTIM22PRSSFXVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:INES2YPZ5DKHFTIM22PRSSFXVA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c6fb4654b36f40baf26f995c3f99c5facfcb1dcce2158771895cab031bcb0ddc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T02:15:29Z","title_canon_sha256":"28fe8f2ea80d4c490bbc7f5e245a2057b6ce82a6af8ef66e46f6bfa23bfb4058"},"schema_version":"1.0","source":{"id":"2501.00031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00031","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00031v1","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00031","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"INES2YPZ5DKH","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_16","alias_value":"INES2YPZ5DKHFTIM","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_8","alias_value":"INES2YPZ","created_at":"2026-07-05T09:55:37Z"}],"graph_snapshots":[{"event_id":"sha256:938b22dcccdf998ef5331afb67ea39380e7bc26920ffb9f99e7a53766eb6fa35","target":"graph","created_at":"2026-07-05T09:55:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.00031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akshay Swaminathan, Annika Gupta, Ivan Lopez, Karthik S. Vedula, Nigam H. Shah, Suhana Bedi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T02:15:29Z","title":"Distilling Large Language Models for Efficient Clinical Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00031","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:472e58d8bc34e3e6e0ee708f1567b65c9e3d8fe8e0b5463e4a9e4a01248b4c2f","target":"record","created_at":"2026-07-05T09:55:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c6fb4654b36f40baf26f995c3f99c5facfcb1dcce2158771895cab031bcb0ddc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T02:15:29Z","title_canon_sha256":"28fe8f2ea80d4c490bbc7f5e245a2057b6ce82a6af8ef66e46f6bfa23bfb4058"},"schema_version":"1.0","source":{"id":"2501.00031","kind":"arxiv","version":1}},"canonical_sha256":"43492d61f9e8d472cd0cd69f1948b7a81f2a44df6e227bd03efd0a7e37be3afc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43492d61f9e8d472cd0cd69f1948b7a81f2a44df6e227bd03efd0a7e37be3afc","first_computed_at":"2026-07-05T09:55:37.939755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:37.939755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wrN+k6oawF7oH4A1eONHtHlNI+C5fQZjy/MiI2P9P5GhnXQPgpG6aaq/XDAO+AZdH9elUVQgr5JuX8NM/PKhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:37.940111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:472e58d8bc34e3e6e0ee708f1567b65c9e3d8fe8e0b5463e4a9e4a01248b4c2f","sha256:938b22dcccdf998ef5331afb67ea39380e7bc26920ffb9f99e7a53766eb6fa35"],"state_sha256":"72ed129f0ef8038c13a3c8eba195e8b2a2839a813f18cfb843bc7a8ea11f6e69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MuD+Q/eJcf9rD0Ub+s50uqgqsisHXkGKzvC2GhX1ZIHIIB29rM3yLHtRvQHDMf50YgHLnIig0Ucsrg5/FBrfBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:22:13.039800Z","bundle_sha256":"dc5c24c027ae2956d387ed40f06aeb8c7fb5ffddb155a140649b580a59918e54"}}