{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CWFKHX5MLZ6KRLBCZ2E3ICX3TS","short_pith_number":"pith:CWFKHX5M","schema_version":"1.0","canonical_sha256":"158aa3dfac5e7ca8ac22ce89b40afb9cb9e4470c3e2185cffacc1225e2bb72db","source":{"kind":"arxiv","id":"2512.01210","version":4},"attestation_state":"computed","paper":{"title":"Knowledge Graph Augmented Large Language Models for Disease Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Carl Yang, Francisco Pasquel, Jiaying Lu, Mohammed K Ali, Ran Xu, Ruiyu Wang, Tuan Vinh, Yuyin Zhou","submitted_at":"2025-12-01T02:49:17Z","abstract_excerpt":"Electronic health records (EHRs) enable strong clinical prediction, but explanations are often coarse and hard to use for patient-level decisions. We propose a knowledge graph (KG)-guided chain-of-thought (CoT) framework for visit-level disease prediction on MIMIC-III. We map ICD-9 codes to PrimeKG, mine disease-relevant nodes and paths, and use these paths to scaffold temporally consistent CoT rationales, retaining only samples whose conclusions match observed outcomes. We fine-tune lightweight instruction-tuned LLMs (LLaMA-3.1-Instruct-8B and Gemma-7B) on two small cohorts (400 and 1,000 ind"},"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":"2512.01210","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-12-01T02:49:17Z","cross_cats_sorted":[],"title_canon_sha256":"034ea7115bea3243b49cc7b33b0eb52193fe3a56b9a97b5e0f4cfa0d33f66048","abstract_canon_sha256":"7a2f23f0ba1554f447befd54b091d9c6fa052e1fe14f74dca29d75872db3e9c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:36:00.188552Z","signature_b64":"D5RT3uleKBP7RY7Y5iOD8Es7cTLZb2io++MMJNgKK7QkHi9K2fbeX1icsDqKsdcOQ0I/YQTwHjlbWzi/8DE+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158aa3dfac5e7ca8ac22ce89b40afb9cb9e4470c3e2185cffacc1225e2bb72db","last_reissued_at":"2026-08-04T00:36:00.187046Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:36:00.187046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graph Augmented Large Language Models for Disease Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Carl Yang, Francisco Pasquel, Jiaying Lu, Mohammed K Ali, Ran Xu, Ruiyu Wang, Tuan Vinh, Yuyin Zhou","submitted_at":"2025-12-01T02:49:17Z","abstract_excerpt":"Electronic health records (EHRs) enable strong clinical prediction, but explanations are often coarse and hard to use for patient-level decisions. We propose a knowledge graph (KG)-guided chain-of-thought (CoT) framework for visit-level disease prediction on MIMIC-III. We map ICD-9 codes to PrimeKG, mine disease-relevant nodes and paths, and use these paths to scaffold temporally consistent CoT rationales, retaining only samples whose conclusions match observed outcomes. We fine-tune lightweight instruction-tuned LLMs (LLaMA-3.1-Instruct-8B and Gemma-7B) on two small cohorts (400 and 1,000 ind"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.01210","kind":"arxiv","version":4},"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/2512.01210/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":"2512.01210","created_at":"2026-08-04T00:36:00.188177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.01210v4","created_at":"2026-08-04T00:36:00.188177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.01210","created_at":"2026-08-04T00:36:00.188177+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWFKHX5MLZ6K","created_at":"2026-08-04T00:36:00.188177+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWFKHX5MLZ6KRLBC","created_at":"2026-08-04T00:36:00.188177+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWFKHX5M","created_at":"2026-08-04T00:36:00.188177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.11675","citing_title":"Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS","json":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS.json","graph_json":"https://pith.science/api/pith-number/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/graph.json","events_json":"https://pith.science/api/pith-number/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/events.json","paper":"https://pith.science/paper/CWFKHX5M"},"agent_actions":{"view_html":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS","download_json":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS.json","view_paper":"https://pith.science/paper/CWFKHX5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.01210&json=true","fetch_graph":"https://pith.science/api/pith-number/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/graph.json","fetch_events":"https://pith.science/api/pith-number/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/action/storage_attestation","attest_author":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/action/author_attestation","sign_citation":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/action/citation_signature","submit_replication":"https://pith.science/pith/CWFKHX5MLZ6KRLBCZ2E3ICX3TS/action/replication_record"}},"created_at":"2026-08-04T00:36:00.188177+00:00","updated_at":"2026-08-04T00:36:00.188177+00:00"}