{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D65WM36CAIHEOZZ575W5EWV2GW","short_pith_number":"pith:D65WM36C","schema_version":"1.0","canonical_sha256":"1fbb666fc2020e47673dff6dd25aba35913d59759805abbbd50428f7f39dc7b5","source":{"kind":"arxiv","id":"2406.18027","version":2},"attestation_state":"computed","paper":{"title":"Automated Clinical Data Extraction with Knowledge Conditioned LLMs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aijing Gao, Asim Kadav, Diya Li, Richard Bourgon, Rui Li","submitted_at":"2024-06-26T02:49:28Z","abstract_excerpt":"The extraction of lung lesion information from clinical and medical imaging reports is crucial for research on and clinical care of lung-related diseases. Large language models (LLMs) can be effective at interpreting unstructured text in reports, but they often hallucinate due to a lack of domain-specific knowledge, leading to reduced accuracy and posing challenges for use in clinical settings. To address this, we propose a novel framework that aligns generated internal knowledge with external knowledge through in-context learning (ICL). Our framework employs a retriever to identify relevant u"},"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":"2406.18027","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T02:49:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4b1dd3a54e8c175d2d88550cf51adee173d79a174a6521542e1186f5d343d4c","abstract_canon_sha256":"8c10123a20b5aa969438f7c0284f896c08296377f60d8b60bd9be6e866395bfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:33.973333Z","signature_b64":"BITaSz+nS9M8HximmX5xXbU6XiW8/ISnyP/NrFXPOVCUQI1GOGmekPQF69VLfpu0/OHuabQe7BB2XtWxVss5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fbb666fc2020e47673dff6dd25aba35913d59759805abbbd50428f7f39dc7b5","last_reissued_at":"2026-07-05T09:35:33.972872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:33.972872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Clinical Data Extraction with Knowledge Conditioned LLMs","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aijing Gao, Asim Kadav, Diya Li, Richard Bourgon, Rui Li","submitted_at":"2024-06-26T02:49:28Z","abstract_excerpt":"The extraction of lung lesion information from clinical and medical imaging reports is crucial for research on and clinical care of lung-related diseases. Large language models (LLMs) can be effective at interpreting unstructured text in reports, but they often hallucinate due to a lack of domain-specific knowledge, leading to reduced accuracy and posing challenges for use in clinical settings. To address this, we propose a novel framework that aligns generated internal knowledge with external knowledge through in-context learning (ICL). Our framework employs a retriever to identify relevant u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18027","kind":"arxiv","version":2},"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/2406.18027/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":"2406.18027","created_at":"2026-07-05T09:35:33.972935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18027v2","created_at":"2026-07-05T09:35:33.972935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18027","created_at":"2026-07-05T09:35:33.972935+00:00"},{"alias_kind":"pith_short_12","alias_value":"D65WM36CAIHE","created_at":"2026-07-05T09:35:33.972935+00:00"},{"alias_kind":"pith_short_16","alias_value":"D65WM36CAIHEOZZ5","created_at":"2026-07-05T09:35:33.972935+00:00"},{"alias_kind":"pith_short_8","alias_value":"D65WM36C","created_at":"2026-07-05T09:35:33.972935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW","json":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW.json","graph_json":"https://pith.science/api/pith-number/D65WM36CAIHEOZZ575W5EWV2GW/graph.json","events_json":"https://pith.science/api/pith-number/D65WM36CAIHEOZZ575W5EWV2GW/events.json","paper":"https://pith.science/paper/D65WM36C"},"agent_actions":{"view_html":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW","download_json":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW.json","view_paper":"https://pith.science/paper/D65WM36C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18027&json=true","fetch_graph":"https://pith.science/api/pith-number/D65WM36CAIHEOZZ575W5EWV2GW/graph.json","fetch_events":"https://pith.science/api/pith-number/D65WM36CAIHEOZZ575W5EWV2GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/action/storage_attestation","attest_author":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/action/author_attestation","sign_citation":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/action/citation_signature","submit_replication":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/action/replication_record"}},"created_at":"2026-07-05T09:35:33.972935+00:00","updated_at":"2026-07-05T09:35:33.972935+00:00"}