{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZE7YUQI6BMXF3AGSPKZ72VY56V","short_pith_number":"pith:ZE7YUQI6","canonical_record":{"source":{"id":"2408.11334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T04:33:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"316351c30052863a5ab030181ec63b3f3f06ee89e06aba44c7ce6dc2f850007b","abstract_canon_sha256":"85c111734af6d202aa24409f73cbae82e1a7f5bf1ce4cc9ac61c813bcedec4e8"},"schema_version":"1.0"},"canonical_sha256":"c93f8a411e0b2e5d80d27ab3fd571df5581a72bd72fd4038c5d1cac0179d921a","source":{"kind":"arxiv","id":"2408.11334","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11334","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11334v1","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11334","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"ZE7YUQI6BMXF","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"ZE7YUQI6BMXF3AGS","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"ZE7YUQI6","created_at":"2026-07-05T08:57:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZE7YUQI6BMXF3AGSPKZ72VY56V","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T04:33:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"316351c30052863a5ab030181ec63b3f3f06ee89e06aba44c7ce6dc2f850007b","abstract_canon_sha256":"85c111734af6d202aa24409f73cbae82e1a7f5bf1ce4cc9ac61c813bcedec4e8"},"schema_version":"1.0"},"canonical_sha256":"c93f8a411e0b2e5d80d27ab3fd571df5581a72bd72fd4038c5d1cac0179d921a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:42.137708Z","signature_b64":"ZWM8yIwL+/5Rfoz8aySv4o4oS1rUsWHBITBbNkUGs9UcuYkOG/F0Fu8VgZe0hmoMh9AZEOERazkZHeN/wYH+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c93f8a411e0b2e5d80d27ab3fd571df5581a72bd72fd4038c5d1cac0179d921a","last_reissued_at":"2026-07-05T08:57:42.137302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:42.137302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11334","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":"2026-07-05T08:57:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mz2Fy1fWg3Ac2QHDwiaN0Fp+DRp8LPBk8yga4zioXJR1zZ+4wjOz24d2+jYpkiU+lIvPlttIAmsTCPbE/3xeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:20:03.475883Z"},"content_sha256":"18b02a099f9c5e14e88b27690027b7e84b360bc04175ded93dd61f74c3501025","schema_version":"1.0","event_id":"sha256:18b02a099f9c5e14e88b27690027b7e84b360bc04175ded93dd61f74c3501025"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZE7YUQI6BMXF3AGSPKZ72VY56V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BURExtract-Llama: An LLM for Clinical Concept Extraction in Breast Ultrasound Reports","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Antonio Verdone, Chen Zhao, Fardeen Siddiqui, Haoyan Yang, Hengkai Pan, Qingyang Zhang, Sumit Chopra, Yiqiu Shen, Yuxuan Chen","submitted_at":"2024-08-21T04:33:05Z","abstract_excerpt":"Breast ultrasound is essential for detecting and diagnosing abnormalities, with radiology reports summarizing key findings like lesion characteristics and malignancy assessments. Extracting this critical information is challenging due to the unstructured nature of these reports, with varied linguistic styles and inconsistent formatting. While proprietary LLMs like GPT-4 are effective, they are costly and raise privacy concerns when handling protected health information. This study presents a pipeline for developing an in-house LLM to extract clinical information from radiology reports. We firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11334","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/2408.11334/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":"2026-07-05T08:57:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zhhWiIqOvJJi16ObOBaS/XSXS+DgdRyuKCUCnsM5a61Ybdmbxwlhrv4V6rApmRbk+whEgJRKY35loPbJcZgpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:20:03.476661Z"},"content_sha256":"37ccd4e7685543a895ef3f27e74968ea20b6106839a3afd1a40297363d899d2c","schema_version":"1.0","event_id":"sha256:37ccd4e7685543a895ef3f27e74968ea20b6106839a3afd1a40297363d899d2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZE7YUQI6BMXF3AGSPKZ72VY56V/bundle.json","state_url":"https://pith.science/pith/ZE7YUQI6BMXF3AGSPKZ72VY56V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZE7YUQI6BMXF3AGSPKZ72VY56V/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":"2026-08-19T23:20:03Z","links":{"resolver":"https://pith.science/pith/ZE7YUQI6BMXF3AGSPKZ72VY56V","bundle":"https://pith.science/pith/ZE7YUQI6BMXF3AGSPKZ72VY56V/bundle.json","state":"https://pith.science/pith/ZE7YUQI6BMXF3AGSPKZ72VY56V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZE7YUQI6BMXF3AGSPKZ72VY56V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZE7YUQI6BMXF3AGSPKZ72VY56V","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":"85c111734af6d202aa24409f73cbae82e1a7f5bf1ce4cc9ac61c813bcedec4e8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T04:33:05Z","title_canon_sha256":"316351c30052863a5ab030181ec63b3f3f06ee89e06aba44c7ce6dc2f850007b"},"schema_version":"1.0","source":{"id":"2408.11334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11334","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11334v1","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11334","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"ZE7YUQI6BMXF","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"ZE7YUQI6BMXF3AGS","created_at":"2026-07-05T08:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"ZE7YUQI6","created_at":"2026-07-05T08:57:42Z"}],"graph_snapshots":[{"event_id":"sha256:37ccd4e7685543a895ef3f27e74968ea20b6106839a3afd1a40297363d899d2c","target":"graph","created_at":"2026-07-05T08:57:42Z","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/2408.11334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Breast ultrasound is essential for detecting and diagnosing abnormalities, with radiology reports summarizing key findings like lesion characteristics and malignancy assessments. Extracting this critical information is challenging due to the unstructured nature of these reports, with varied linguistic styles and inconsistent formatting. While proprietary LLMs like GPT-4 are effective, they are costly and raise privacy concerns when handling protected health information. This study presents a pipeline for developing an in-house LLM to extract clinical information from radiology reports. We firs","authors_text":"Antonio Verdone, Chen Zhao, Fardeen Siddiqui, Haoyan Yang, Hengkai Pan, Qingyang Zhang, Sumit Chopra, Yiqiu Shen, Yuxuan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T04:33:05Z","title":"BURExtract-Llama: An LLM for Clinical Concept Extraction in Breast Ultrasound Reports"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11334","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":"sha256:18b02a099f9c5e14e88b27690027b7e84b360bc04175ded93dd61f74c3501025","target":"record","created_at":"2026-07-05T08:57:42Z","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":"85c111734af6d202aa24409f73cbae82e1a7f5bf1ce4cc9ac61c813bcedec4e8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T04:33:05Z","title_canon_sha256":"316351c30052863a5ab030181ec63b3f3f06ee89e06aba44c7ce6dc2f850007b"},"schema_version":"1.0","source":{"id":"2408.11334","kind":"arxiv","version":1}},"canonical_sha256":"c93f8a411e0b2e5d80d27ab3fd571df5581a72bd72fd4038c5d1cac0179d921a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c93f8a411e0b2e5d80d27ab3fd571df5581a72bd72fd4038c5d1cac0179d921a","first_computed_at":"2026-07-05T08:57:42.137302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:42.137302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZWM8yIwL+/5Rfoz8aySv4o4oS1rUsWHBITBbNkUGs9UcuYkOG/F0Fu8VgZe0hmoMh9AZEOERazkZHeN/wYH+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:42.137708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18b02a099f9c5e14e88b27690027b7e84b360bc04175ded93dd61f74c3501025","sha256:37ccd4e7685543a895ef3f27e74968ea20b6106839a3afd1a40297363d899d2c"],"state_sha256":"7b868fdc53b5f0623c5e403390bc57b400741bbe9e02ce31b5e40b675c587b09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ql93jvz0huqAjng2pgTlrtOmkSWX2N19hwN/J6rveVTIlbzfHWjCQBuVO4s30Pz83qdLDsC9f97fTwMVK1+aAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:20:03.482296Z","bundle_sha256":"5bd6a45e7cad361fd64c2b91903850ceccd9c32b747b8c9a772bc726e421c860"}}