{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ROOEMDTZHKXTKNV4J3KQ4FZ665","short_pith_number":"pith:ROOEMDTZ","schema_version":"1.0","canonical_sha256":"8b9c460e793aaf3536bc4ed50e173ef7674428193647f5f8f2cdc8ee5b98833a","source":{"kind":"arxiv","id":"2410.04585","version":2},"attestation_state":"computed","paper":{"title":"Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cao Xiao, Jiawei Han, Jimeng Sun, Minhao Jiang, Parminder Bhatia, Pengcheng Jiang, Taha Kass-hout","submitted_at":"2024-10-06T18:46:28Z","abstract_excerpt":"Large language models (LLMs) have demonstrated significant potential in clinical decision support. Yet LLMs still suffer from hallucinations and lack fine-grained contextual medical knowledge, limiting their high-stake healthcare applications such as clinical diagnosis. Traditional retrieval-augmented generation (RAG) methods attempt to address these limitations but frequently retrieve sparse or irrelevant information, undermining prediction accuracy. We introduce KARE, a novel framework that integrates knowledge graph (KG) community-level retrieval with LLM reasoning to enhance healthcare pre"},"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":"2410.04585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-06T18:46:28Z","cross_cats_sorted":[],"title_canon_sha256":"14860c9a8c784f7e885f481b202ce8ffa5783f2ece121061df0b26ea0033f30d","abstract_canon_sha256":"ec3acee1b862c52e5409b9526a3694be5bce9a7d3d78f5961d25e967224b1f4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:25.985887Z","signature_b64":"LhnGWU7WBnVHZDj3167uJQd4GphcIuNAkx9WNd6C7TBST0M6SRQN20RdsJy4onOXdi0kB3etieokkAUJJLfxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b9c460e793aaf3536bc4ed50e173ef7674428193647f5f8f2cdc8ee5b98833a","last_reissued_at":"2026-07-05T10:51:25.985370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:25.985370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cao Xiao, Jiawei Han, Jimeng Sun, Minhao Jiang, Parminder Bhatia, Pengcheng Jiang, Taha Kass-hout","submitted_at":"2024-10-06T18:46:28Z","abstract_excerpt":"Large language models (LLMs) have demonstrated significant potential in clinical decision support. Yet LLMs still suffer from hallucinations and lack fine-grained contextual medical knowledge, limiting their high-stake healthcare applications such as clinical diagnosis. Traditional retrieval-augmented generation (RAG) methods attempt to address these limitations but frequently retrieve sparse or irrelevant information, undermining prediction accuracy. We introduce KARE, a novel framework that integrates knowledge graph (KG) community-level retrieval with LLM reasoning to enhance healthcare pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04585","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/2410.04585/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":"2410.04585","created_at":"2026-07-05T10:51:25.985429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04585v2","created_at":"2026-07-05T10:51:25.985429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04585","created_at":"2026-07-05T10:51:25.985429+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROOEMDTZHKXT","created_at":"2026-07-05T10:51:25.985429+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROOEMDTZHKXTKNV4","created_at":"2026-07-05T10:51:25.985429+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROOEMDTZ","created_at":"2026-07-05T10:51:25.985429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15016","citing_title":"COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13331","citing_title":"Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10455","citing_title":"EviCare: Enhancing Diagnosis Prediction with Deep Model-Guided Evidence for In-Context Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07659","citing_title":"Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06603","citing_title":"Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665","json":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665.json","graph_json":"https://pith.science/api/pith-number/ROOEMDTZHKXTKNV4J3KQ4FZ665/graph.json","events_json":"https://pith.science/api/pith-number/ROOEMDTZHKXTKNV4J3KQ4FZ665/events.json","paper":"https://pith.science/paper/ROOEMDTZ"},"agent_actions":{"view_html":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665","download_json":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665.json","view_paper":"https://pith.science/paper/ROOEMDTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04585&json=true","fetch_graph":"https://pith.science/api/pith-number/ROOEMDTZHKXTKNV4J3KQ4FZ665/graph.json","fetch_events":"https://pith.science/api/pith-number/ROOEMDTZHKXTKNV4J3KQ4FZ665/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665/action/storage_attestation","attest_author":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665/action/author_attestation","sign_citation":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665/action/citation_signature","submit_replication":"https://pith.science/pith/ROOEMDTZHKXTKNV4J3KQ4FZ665/action/replication_record"}},"created_at":"2026-07-05T10:51:25.985429+00:00","updated_at":"2026-07-05T10:51:25.985429+00:00"}