{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YUSN3B6YAFQACKGBQYWJBED5QB","short_pith_number":"pith:YUSN3B6Y","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"},"canonical_sha256":"c524dd87d801600128c1862c90907d80761dbb53f349e4f815b6d06699f15a19","source":{"kind":"arxiv","id":"2409.10576","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10576","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10576v2","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10576","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"YUSN3B6YAFQA","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"YUSN3B6YAFQACKGB","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"YUSN3B6Y","created_at":"2026-07-05T09:08:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YUSN3B6YAFQACKGBQYWJBED5QB","target":"record","payload":{"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"},"canonical_sha256":"c524dd87d801600128c1862c90907d80761dbb53f349e4f815b6d06699f15a19","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"},"source_kind":"arxiv","source_id":"2409.10576","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+CdbNC21MwhCbYDlHkYVmsV3k7cYupb0hUGbEuBIdHPa8Cr968Bcobk4G5llY9CmxzYy+BZFgjDWXv0hrfYTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:49:56.067814Z"},"content_sha256":"d27ec4b36542514f358d65aed4ef6e160c0e44a0e87c1063b55ae6c54452dec1","schema_version":"1.0","event_id":"sha256:d27ec4b36542514f358d65aed4ef6e160c0e44a0e87c1063b55ae6c54452dec1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YUSN3B6YAFQACKGBQYWJBED5QB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nq6D5YxuGf4rtPgMluVwPpiHNVy/2e7nl7e+UDvzk3sFKYQIiDxtjgyclNKgZGrdhADm7l2Ua9f+K9DXB/EBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:49:56.068308Z"},"content_sha256":"fc3c2a774fe936f83ce315bb010c1a87920962a9b1942a2514bbe0c6d53b457a","schema_version":"1.0","event_id":"sha256:fc3c2a774fe936f83ce315bb010c1a87920962a9b1942a2514bbe0c6d53b457a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/bundle.json","state_url":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YUSN3B6YAFQACKGBQYWJBED5QB/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":"2026-07-31T18:49:56Z","links":{"resolver":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB","bundle":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/bundle.json","state":"https://pith.science/pith/YUSN3B6YAFQACKGBQYWJBED5QB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YUSN3B6YAFQACKGBQYWJBED5QB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YUSN3B6YAFQACKGBQYWJBED5QB","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":"90fd86fca7914bf09375a6a2d193ff596314cecf7dc824a5f502aba98427a4d2","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T15:21:45Z","title_canon_sha256":"7277e9a3914b620b6dc68b084145fa8c4c5b2a34a185b2d34ddfc0fab593265f"},"schema_version":"1.0","source":{"id":"2409.10576","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10576","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10576v2","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10576","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_12","alias_value":"YUSN3B6YAFQA","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_16","alias_value":"YUSN3B6YAFQACKGB","created_at":"2026-07-05T09:08:29Z"},{"alias_kind":"pith_short_8","alias_value":"YUSN3B6Y","created_at":"2026-07-05T09:08:29Z"}],"graph_snapshots":[{"event_id":"sha256:fc3c2a774fe936f83ce315bb010c1a87920962a9b1942a2514bbe0c6d53b457a","target":"graph","created_at":"2026-07-05T09:08:29Z","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/2409.10576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Ayush Jain, Evan Calabrese, Jikai Zhang, Kartikeye Gupta, Kirti Magudia, Maciej Mazurowski, Mohamed Sobhi Jabal, Pranav Warman, Walter Wiggins","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T15:21:45Z","title":"Language Models and Retrieval Augmented Generation for Automated Structured Data Extraction from Diagnostic Reports"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10576","kind":"arxiv","version":2},"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:d27ec4b36542514f358d65aed4ef6e160c0e44a0e87c1063b55ae6c54452dec1","target":"record","created_at":"2026-07-05T09:08:29Z","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":"90fd86fca7914bf09375a6a2d193ff596314cecf7dc824a5f502aba98427a4d2","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T15:21:45Z","title_canon_sha256":"7277e9a3914b620b6dc68b084145fa8c4c5b2a34a185b2d34ddfc0fab593265f"},"schema_version":"1.0","source":{"id":"2409.10576","kind":"arxiv","version":2}},"canonical_sha256":"c524dd87d801600128c1862c90907d80761dbb53f349e4f815b6d06699f15a19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c524dd87d801600128c1862c90907d80761dbb53f349e4f815b6d06699f15a19","first_computed_at":"2026-07-05T09:08:29.836649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:29.836649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/go9sBCAzKPBnadiqdC/IXTCTRoJmf7dK/9hfI8PDKuaKFfpQ0bPqUJ/xcX5JrXnMToifwBzzQoX+CpzIGNGDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:29.837127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10576","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d27ec4b36542514f358d65aed4ef6e160c0e44a0e87c1063b55ae6c54452dec1","sha256:fc3c2a774fe936f83ce315bb010c1a87920962a9b1942a2514bbe0c6d53b457a"],"state_sha256":"30de949530acce2a1c3274fd30df464ea8159c00b55175150a6ac9a58b67c85d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kBzHtWdv92TiEdDXQHe4bTqHoxjAGJOMLP3gqSujONBb1B6ogVqRd3TXrxzqTkd+F1fXQcIUUAkGh4lbpZooDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T18:49:56.073487Z","bundle_sha256":"196aff8f228834a25a0242d212e08c4205022a9e5838e84b6d96a90378b997c5"}}