{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OBWMVG2COSWTEX6PDGUNQ3ZK3Z","short_pith_number":"pith:OBWMVG2C","schema_version":"1.0","canonical_sha256":"706cca9b4274ad325fcf19a8d86f2ade75b9ac63fac7a71cb23928e796cb1617","source":{"kind":"arxiv","id":"2402.07016","version":1},"attestation_state":"computed","paper":{"title":"REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changyu Ren, Chengwei Pan, Hangyuan Ji, Long He, Shiyun Xie, Shukai Liu, Tao Sun, Xi Zhu, Yinghao Zhu, Zhoujun Li, Zixiang Wang","submitted_at":"2024-02-10T18:27:28Z","abstract_excerpt":"The integration of multimodal Electronic Health Records (EHR) data has significantly improved clinical predictive capabilities. Leveraging clinical notes and multivariate time-series EHR, existing models often lack the medical context relevent to clinical tasks, prompting the incorporation of external knowledge, particularly from the knowledge graph (KG). Previous approaches with KG knowledge have primarily focused on structured knowledge extraction, neglecting unstructured data modalities and semantic high dimensional medical knowledge. In response, we propose REALM, a Retrieval-Augmented Gen"},"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":"2402.07016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-10T18:27:28Z","cross_cats_sorted":[],"title_canon_sha256":"0453598be51e319bfe4893fa40d4632abc591cfa14f2e587635858b7e8bb6654","abstract_canon_sha256":"63f29d5cd83586b63395748dad688103ee2f1335a69f418de8453c1abafa8006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:42.305669Z","signature_b64":"68H8n23iAzzdWTmlVHpgLQbT/3gGtlqOIVEyav7qDhL3ipMe4prUtT+EdVnu2nO2E165SuL/b8NlnTCnEIx5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"706cca9b4274ad325fcf19a8d86f2ade75b9ac63fac7a71cb23928e796cb1617","last_reissued_at":"2026-07-05T07:43:42.305158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:42.305158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changyu Ren, Chengwei Pan, Hangyuan Ji, Long He, Shiyun Xie, Shukai Liu, Tao Sun, Xi Zhu, Yinghao Zhu, Zhoujun Li, Zixiang Wang","submitted_at":"2024-02-10T18:27:28Z","abstract_excerpt":"The integration of multimodal Electronic Health Records (EHR) data has significantly improved clinical predictive capabilities. Leveraging clinical notes and multivariate time-series EHR, existing models often lack the medical context relevent to clinical tasks, prompting the incorporation of external knowledge, particularly from the knowledge graph (KG). Previous approaches with KG knowledge have primarily focused on structured knowledge extraction, neglecting unstructured data modalities and semantic high dimensional medical knowledge. In response, we propose REALM, a Retrieval-Augmented Gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07016","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/2402.07016/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":"2402.07016","created_at":"2026-07-05T07:43:42.305211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07016v1","created_at":"2026-07-05T07:43:42.305211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07016","created_at":"2026-07-05T07:43:42.305211+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBWMVG2COSWT","created_at":"2026-07-05T07:43:42.305211+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBWMVG2COSWTEX6P","created_at":"2026-07-05T07:43:42.305211+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBWMVG2C","created_at":"2026-07-05T07:43:42.305211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31010","citing_title":"MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11512","citing_title":"From Time Series Analysis to Question Answering: A Survey in the LLM Era","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02501","citing_title":"ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12335","citing_title":"EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z","json":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z.json","graph_json":"https://pith.science/api/pith-number/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/graph.json","events_json":"https://pith.science/api/pith-number/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/events.json","paper":"https://pith.science/paper/OBWMVG2C"},"agent_actions":{"view_html":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z","download_json":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z.json","view_paper":"https://pith.science/paper/OBWMVG2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07016&json=true","fetch_graph":"https://pith.science/api/pith-number/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/action/storage_attestation","attest_author":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/action/author_attestation","sign_citation":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/action/citation_signature","submit_replication":"https://pith.science/pith/OBWMVG2COSWTEX6PDGUNQ3ZK3Z/action/replication_record"}},"created_at":"2026-07-05T07:43:42.305211+00:00","updated_at":"2026-07-05T07:43:42.305211+00:00"}