{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IPTUZEPZDMVKJNHHNFRRRJCOSZ","short_pith_number":"pith:IPTUZEPZ","canonical_record":{"source":{"id":"2503.12286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-15T22:57:31Z","cross_cats_sorted":["cs.AI","q-bio.GN","q-bio.QM"],"title_canon_sha256":"77792ada23f2737fbab2024678d7c413f6046168e6e36d41bc8fe0d3d2d3811b","abstract_canon_sha256":"29ad00f00e3135eab01f79248fef40d0db7644abb7332c2ac793b764522d1c45"},"schema_version":"1.0"},"canonical_sha256":"43e74c91f91b2aa4b4e7696318a44e9649bd7748ef9891afebf1e809ec14c979","source":{"kind":"arxiv","id":"2503.12286","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12286","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12286v2","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12286","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"pith_short_12","alias_value":"IPTUZEPZDMVK","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"pith_short_16","alias_value":"IPTUZEPZDMVKJNHH","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"pith_short_8","alias_value":"IPTUZEPZ","created_at":"2026-07-15T00:21:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IPTUZEPZDMVKJNHHNFRRRJCOSZ","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-15T22:57:31Z","cross_cats_sorted":["cs.AI","q-bio.GN","q-bio.QM"],"title_canon_sha256":"77792ada23f2737fbab2024678d7c413f6046168e6e36d41bc8fe0d3d2d3811b","abstract_canon_sha256":"29ad00f00e3135eab01f79248fef40d0db7644abb7332c2ac793b764522d1c45"},"schema_version":"1.0"},"canonical_sha256":"43e74c91f91b2aa4b4e7696318a44e9649bd7748ef9891afebf1e809ec14c979","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T00:21:11.304515Z","signature_b64":"B4DjLcGsYg3BBnMlXmOyQzIje6FSJGpNMghsqyRhXLfk4aSBt/zJ9+wxDL3BfFC3FIHVtDlJieWcgV7Ddy/RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43e74c91f91b2aa4b4e7696318a44e9649bd7748ef9891afebf1e809ec14c979","last_reissued_at":"2026-07-15T00:21:11.303602Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T00:21:11.303602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12286","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":"2026-07-15T00:21:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+0PfF+X11DmBitPyMUpfa2JkcmfeubDsGV2OCAExCFWX44hNJOOolf2ti3rxNVEvnTb0lQw5ixU8CELBcThAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T07:59:55.197550Z"},"content_sha256":"00e252d874c043e57700a57782d0231aacf770fa50228e3f02411d94bddf7976","schema_version":"1.0","event_id":"sha256:00e252d874c043e57700a57782d0231aacf770fa50228e3f02411d94bddf7976"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IPTUZEPZDMVKJNHHNFRRRJCOSZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.GN","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Da Wu, Kai Wang, Quan Nguyen, Zhanliang Wang","submitted_at":"2025-03-15T22:57:31Z","abstract_excerpt":"Background: Several studies show that large language models (LLMs) struggle with phenotype-driven gene prioritization for rare diseases. These studies typically use Human Phenotype Ontology (HPO) terms to prompt foundation models like GPT and LLaMA to predict candidate genes. However, in real-world settings, foundation models are not optimized for domain-specific tasks like clinical diagnosis, yet inputs are unstructured clinical notes rather than standardized terms. How LLMs can be instructed to predict candidate genes or disease diagnosis from unstructured clinical notes remains a major chal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12286","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/2503.12286/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":"2026-07-15T00:21:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5uwJC1RW1PIp0Me338OZ+Oub65HS7uj0Qr5dPk4HRVShQVA/Z5iHMFYIGd8H5HcCHP+JiEa1Os1vSYNqZOXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T07:59:55.197927Z"},"content_sha256":"53a03bec07aa33e8a9d2a7000505e40ec00295ba6714c2a631e40cff8009320e","schema_version":"1.0","event_id":"sha256:53a03bec07aa33e8a9d2a7000505e40ec00295ba6714c2a631e40cff8009320e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IPTUZEPZDMVKJNHHNFRRRJCOSZ/bundle.json","state_url":"https://pith.science/pith/IPTUZEPZDMVKJNHHNFRRRJCOSZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IPTUZEPZDMVKJNHHNFRRRJCOSZ/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":"2026-07-27T07:59:55Z","links":{"resolver":"https://pith.science/pith/IPTUZEPZDMVKJNHHNFRRRJCOSZ","bundle":"https://pith.science/pith/IPTUZEPZDMVKJNHHNFRRRJCOSZ/bundle.json","state":"https://pith.science/pith/IPTUZEPZDMVKJNHHNFRRRJCOSZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IPTUZEPZDMVKJNHHNFRRRJCOSZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IPTUZEPZDMVKJNHHNFRRRJCOSZ","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":"29ad00f00e3135eab01f79248fef40d0db7644abb7332c2ac793b764522d1c45","cross_cats_sorted":["cs.AI","q-bio.GN","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-15T22:57:31Z","title_canon_sha256":"77792ada23f2737fbab2024678d7c413f6046168e6e36d41bc8fe0d3d2d3811b"},"schema_version":"1.0","source":{"id":"2503.12286","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12286","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12286v2","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12286","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"pith_short_12","alias_value":"IPTUZEPZDMVK","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"pith_short_16","alias_value":"IPTUZEPZDMVKJNHH","created_at":"2026-07-15T00:21:11Z"},{"alias_kind":"pith_short_8","alias_value":"IPTUZEPZ","created_at":"2026-07-15T00:21:11Z"}],"graph_snapshots":[{"event_id":"sha256:53a03bec07aa33e8a9d2a7000505e40ec00295ba6714c2a631e40cff8009320e","target":"graph","created_at":"2026-07-15T00:21:11Z","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/2503.12286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background: Several studies show that large language models (LLMs) struggle with phenotype-driven gene prioritization for rare diseases. These studies typically use Human Phenotype Ontology (HPO) terms to prompt foundation models like GPT and LLaMA to predict candidate genes. However, in real-world settings, foundation models are not optimized for domain-specific tasks like clinical diagnosis, yet inputs are unstructured clinical notes rather than standardized terms. How LLMs can be instructed to predict candidate genes or disease diagnosis from unstructured clinical notes remains a major chal","authors_text":"Da Wu, Kai Wang, Quan Nguyen, Zhanliang Wang","cross_cats":["cs.AI","q-bio.GN","q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-15T22:57:31Z","title":"Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12286","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":"sha256:00e252d874c043e57700a57782d0231aacf770fa50228e3f02411d94bddf7976","target":"record","created_at":"2026-07-15T00:21:11Z","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":"29ad00f00e3135eab01f79248fef40d0db7644abb7332c2ac793b764522d1c45","cross_cats_sorted":["cs.AI","q-bio.GN","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-15T22:57:31Z","title_canon_sha256":"77792ada23f2737fbab2024678d7c413f6046168e6e36d41bc8fe0d3d2d3811b"},"schema_version":"1.0","source":{"id":"2503.12286","kind":"arxiv","version":2}},"canonical_sha256":"43e74c91f91b2aa4b4e7696318a44e9649bd7748ef9891afebf1e809ec14c979","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43e74c91f91b2aa4b4e7696318a44e9649bd7748ef9891afebf1e809ec14c979","first_computed_at":"2026-07-15T00:21:11.303602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T00:21:11.303602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B4DjLcGsYg3BBnMlXmOyQzIje6FSJGpNMghsqyRhXLfk4aSBt/zJ9+wxDL3BfFC3FIHVtDlJieWcgV7Ddy/RDw==","signature_status":"signed_v1","signed_at":"2026-07-15T00:21:11.304515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12286","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00e252d874c043e57700a57782d0231aacf770fa50228e3f02411d94bddf7976","sha256:53a03bec07aa33e8a9d2a7000505e40ec00295ba6714c2a631e40cff8009320e"],"state_sha256":"1f1d43b5afe199916aba1c458623cf9f1f504d348e3f09c53031738f1d237adc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oR4uRxWcoOH3+SzYJQ6TdYDugK4eH8No4FO1x1sVoecKEYrHD55t6RPfmndgHdYz10vN/Z3IM1AzS/4RWJQKAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T07:59:55.200037Z","bundle_sha256":"87bc257073d7ee2785b823f851764801d4bc707331865176db640aa8732776e7"}}