{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YUSN3B6YAFQACKGBQYWJBED5QB","short_pith_number":"pith:YUSN3B6Y","schema_version":"1.0","canonical_sha256":"c524dd87d801600128c1862c90907d80761dbb53f349e4f815b6d06699f15a19","source":{"kind":"arxiv","id":"2409.10576","version":2},"attestation_state":"computed","paper":{"title":"Language Models and Retrieval Augmented Generation for Automated Structured Data Extraction from Diagnostic Reports","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ayush Jain, Evan Calabrese, Jikai Zhang, Kartikeye Gupta, Kirti Magudia, Maciej Mazurowski, Mohamed Sobhi Jabal, Pranav Warman, Walter Wiggins","submitted_at":"2024-09-15T15:21:45Z","abstract_excerpt":"Purpose: To develop and evaluate an automated system for extracting structured clinical information from unstructured radiology and pathology reports using open-weights large language models (LMs) and retrieval augmented generation (RAG), and to assess the effects of model configuration variables on extraction performance. Methods and Materials: The study utilized two datasets: 7,294 radiology reports annotated for Brain Tumor Reporting and Data System (BT-RADS) scores and 2,154 pathology reports annotated for isocitrate dehydrogenase (IDH) mutation status. An automated pipeline was developed "},"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":"2409.10576","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T15:21:45Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"7277e9a3914b620b6dc68b084145fa8c4c5b2a34a185b2d34ddfc0fab593265f","abstract_canon_sha256":"90fd86fca7914bf09375a6a2d193ff596314cecf7dc824a5f502aba98427a4d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:29.837127Z","signature_b64":"/go9sBCAzKPBnadiqdC/IXTCTRoJmf7dK/9hfI8PDKuaKFfpQ0bPqUJ/xcX5JrXnMToifwBzzQoX+CpzIGNGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c524dd87d801600128c1862c90907d80761dbb53f349e4f815b6d06699f15a19","last_reissued_at":"2026-07-05T09:08:29.836649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:29.836649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models and Retrieval Augmented Generation for Automated Structured Data Extraction from Diagnostic Reports","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ayush Jain, Evan Calabrese, Jikai Zhang, Kartikeye Gupta, Kirti Magudia, Maciej Mazurowski, Mohamed Sobhi Jabal, Pranav Warman, Walter Wiggins","submitted_at":"2024-09-15T15:21:45Z","abstract_excerpt":"Purpose: To develop and evaluate an automated system for extracting structured clinical information from unstructured radiology and pathology reports using open-weights large language models (LMs) and retrieval augmented generation (RAG), and to assess the effects of model configuration variables on extraction performance. Methods and Materials: The study utilized two datasets: 7,294 radiology reports annotated for Brain Tumor Reporting and Data System (BT-RADS) scores and 2,154 pathology reports annotated for isocitrate dehydrogenase (IDH) mutation status. An automated pipeline was developed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10576","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/2409.10576/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":"2409.10576","created_at":"2026-07-05T09:08:29.836716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10576v2","created_at":"2026-07-05T09:08:29.836716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10576","created_at":"2026-07-05T09:08:29.836716+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUSN3B6YAFQA","created_at":"2026-07-05T09:08:29.836716+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUSN3B6YAFQACKGB","created_at":"2026-07-05T09:08:29.836716+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUSN3B6Y","created_at":"2026-07-05T09:08:29.836716+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/YUSN3B6YAFQACKGBQYWJBED5QB","json":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB.json","graph_json":"https://pith.science/api/pith-number/YUSN3B6YAFQACKGBQYWJBED5QB/graph.json","events_json":"https://pith.science/api/pith-number/YUSN3B6YAFQACKGBQYWJBED5QB/events.json","paper":"https://pith.science/paper/YUSN3B6Y"},"agent_actions":{"view_html":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB","download_json":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB.json","view_paper":"https://pith.science/paper/YUSN3B6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10576&json=true","fetch_graph":"https://pith.science/api/pith-number/YUSN3B6YAFQACKGBQYWJBED5QB/graph.json","fetch_events":"https://pith.science/api/pith-number/YUSN3B6YAFQACKGBQYWJBED5QB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/action/storage_attestation","attest_author":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/action/author_attestation","sign_citation":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/action/citation_signature","submit_replication":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/action/replication_record"}},"created_at":"2026-07-05T09:08:29.836716+00:00","updated_at":"2026-07-05T09:08:29.836716+00:00"}