{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D65WM36CAIHEOZZ575W5EWV2GW","short_pith_number":"pith:D65WM36C","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"},"canonical_sha256":"1fbb666fc2020e47673dff6dd25aba35913d59759805abbbd50428f7f39dc7b5","source":{"kind":"arxiv","id":"2406.18027","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18027","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18027v2","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18027","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"pith_short_12","alias_value":"D65WM36CAIHE","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"pith_short_16","alias_value":"D65WM36CAIHEOZZ5","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"pith_short_8","alias_value":"D65WM36C","created_at":"2026-07-05T09:35:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D65WM36CAIHEOZZ575W5EWV2GW","target":"record","payload":{"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"},"canonical_sha256":"1fbb666fc2020e47673dff6dd25aba35913d59759805abbbd50428f7f39dc7b5","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"},"source_kind":"arxiv","source_id":"2406.18027","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":"2026-07-05T09:35:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDCsEkyjL071FJeZByHXs2KodF8frux9Dohe863PkChxfMoA7TqlHZsCX5nQOeylqdinNY6OypEEeVMzNnYKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:49:04.070561Z"},"content_sha256":"60a55319ffca8e73c57e57fc78719cf1e509e9168ff6d7017ed69fa66e496213","schema_version":"1.0","event_id":"sha256:60a55319ffca8e73c57e57fc78719cf1e509e9168ff6d7017ed69fa66e496213"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D65WM36CAIHEOZZ575W5EWV2GW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:35:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ppMGJJuWNE/ICVBH6Swus5OXTsr9hG3E4p+4t7ETDIdTyV1Z8XIL9008gzDIrQDo6WSdLsez1W3Q/LIOfeddCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T07:49:04.071458Z"},"content_sha256":"f2cd865985eee18ffd5cc073c841d2d32925bc155be127d965a39aa92bd61858","schema_version":"1.0","event_id":"sha256:f2cd865985eee18ffd5cc073c841d2d32925bc155be127d965a39aa92bd61858"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/bundle.json","state_url":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D65WM36CAIHEOZZ575W5EWV2GW/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":"2026-08-13T07:49:04Z","links":{"resolver":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW","bundle":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/bundle.json","state":"https://pith.science/pith/D65WM36CAIHEOZZ575W5EWV2GW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D65WM36CAIHEOZZ575W5EWV2GW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D65WM36CAIHEOZZ575W5EWV2GW","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":"8c10123a20b5aa969438f7c0284f896c08296377f60d8b60bd9be6e866395bfb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T02:49:28Z","title_canon_sha256":"a4b1dd3a54e8c175d2d88550cf51adee173d79a174a6521542e1186f5d343d4c"},"schema_version":"1.0","source":{"id":"2406.18027","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18027","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18027v2","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18027","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"pith_short_12","alias_value":"D65WM36CAIHE","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"pith_short_16","alias_value":"D65WM36CAIHEOZZ5","created_at":"2026-07-05T09:35:33Z"},{"alias_kind":"pith_short_8","alias_value":"D65WM36C","created_at":"2026-07-05T09:35:33Z"}],"graph_snapshots":[{"event_id":"sha256:f2cd865985eee18ffd5cc073c841d2d32925bc155be127d965a39aa92bd61858","target":"graph","created_at":"2026-07-05T09:35:33Z","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/2406.18027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aijing Gao, Asim Kadav, Diya Li, Richard Bourgon, Rui Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T02:49:28Z","title":"Automated Clinical Data Extraction with Knowledge Conditioned LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18027","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":"sha256:60a55319ffca8e73c57e57fc78719cf1e509e9168ff6d7017ed69fa66e496213","target":"record","created_at":"2026-07-05T09:35:33Z","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":"8c10123a20b5aa969438f7c0284f896c08296377f60d8b60bd9be6e866395bfb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T02:49:28Z","title_canon_sha256":"a4b1dd3a54e8c175d2d88550cf51adee173d79a174a6521542e1186f5d343d4c"},"schema_version":"1.0","source":{"id":"2406.18027","kind":"arxiv","version":2}},"canonical_sha256":"1fbb666fc2020e47673dff6dd25aba35913d59759805abbbd50428f7f39dc7b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fbb666fc2020e47673dff6dd25aba35913d59759805abbbd50428f7f39dc7b5","first_computed_at":"2026-07-05T09:35:33.972872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:33.972872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BITaSz+nS9M8HximmX5xXbU6XiW8/ISnyP/NrFXPOVCUQI1GOGmekPQF69VLfpu0/OHuabQe7BB2XtWxVss5Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:33.973333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18027","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60a55319ffca8e73c57e57fc78719cf1e509e9168ff6d7017ed69fa66e496213","sha256:f2cd865985eee18ffd5cc073c841d2d32925bc155be127d965a39aa92bd61858"],"state_sha256":"1043f770c81c256856bd24a313c4ab2e5ec7a05a1a100e50d760ffb5e493326b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1TADuFqEz6wc+e6AE8cQkbmmOZ72uWY/NQYDoQ2ltgBvnfOPgiaZ++RiGM0k1RWIQq7SmYcCdW5+br4AIBctBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T07:49:04.077526Z","bundle_sha256":"58b067f2757984eca6d541b56cffb0e38dce24978dd9d9e144212a1ce99ced3a"}}