{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QBFBEXOED7TQC2H7UNFMOX7N6D","short_pith_number":"pith:QBFBEXOE","schema_version":"1.0","canonical_sha256":"804a125dc41fe70168ffa34ac75fedf0e4e6c2c6e3c36b453b8fa3a6e10f45e0","source":{"kind":"arxiv","id":"2403.00815","version":3},"attestation_state":"computed","paper":{"title":"RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","q-bio.OT"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Carl Yang, Joyce C. Ho, May D. Wang, Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu","submitted_at":"2024-02-25T23:10:20Z","abstract_excerpt":"We present RAM-EHR, a Retrieval AugMentation pipeline to improve clinical predictions on Electronic Health Records (EHRs). RAM-EHR first collects multiple knowledge sources, converts them into text format, and uses dense retrieval to obtain information related to medical concepts. This strategy addresses the difficulties associated with complex names for the concepts. RAM-EHR then augments the local EHR predictive model co-trained with consistency regularization to capture complementary information from patient visits and summarized knowledge. Experiments on two EHR datasets show the efficacy "},"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":"2403.00815","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T23:10:20Z","cross_cats_sorted":["cs.AI","cs.IR","q-bio.OT"],"title_canon_sha256":"9ee8c6383a990d3f594f8ade62653ad6b0248c253ceedbb8885332e4bb7144fc","abstract_canon_sha256":"6afef594ae51134ef1a732b5b9ad8a7a3e9c0b717ec20fd2618528eb3b0e3396"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:59.889069Z","signature_b64":"JBHL9YOtwbE0h6DuMuSRm8Fc0Xv+BZBVEUr7bFlijS6jueP1VpMtiAYEIbEWUtNWA+M7oEkEgLjkfaWn+g+RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"804a125dc41fe70168ffa34ac75fedf0e4e6c2c6e3c36b453b8fa3a6e10f45e0","last_reissued_at":"2026-07-05T08:48:59.888582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:59.888582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","q-bio.OT"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Carl Yang, Joyce C. Ho, May D. Wang, Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu","submitted_at":"2024-02-25T23:10:20Z","abstract_excerpt":"We present RAM-EHR, a Retrieval AugMentation pipeline to improve clinical predictions on Electronic Health Records (EHRs). RAM-EHR first collects multiple knowledge sources, converts them into text format, and uses dense retrieval to obtain information related to medical concepts. This strategy addresses the difficulties associated with complex names for the concepts. RAM-EHR then augments the local EHR predictive model co-trained with consistency regularization to capture complementary information from patient visits and summarized knowledge. Experiments on two EHR datasets show the efficacy "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00815","kind":"arxiv","version":3},"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/2403.00815/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":"2403.00815","created_at":"2026-07-05T08:48:59.888642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00815v3","created_at":"2026-07-05T08:48:59.888642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00815","created_at":"2026-07-05T08:48:59.888642+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBFBEXOED7TQ","created_at":"2026-07-05T08:48:59.888642+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBFBEXOED7TQC2H7","created_at":"2026-07-05T08:48:59.888642+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBFBEXOE","created_at":"2026-07-05T08:48:59.888642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21320","citing_title":"Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D","json":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D.json","graph_json":"https://pith.science/api/pith-number/QBFBEXOED7TQC2H7UNFMOX7N6D/graph.json","events_json":"https://pith.science/api/pith-number/QBFBEXOED7TQC2H7UNFMOX7N6D/events.json","paper":"https://pith.science/paper/QBFBEXOE"},"agent_actions":{"view_html":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D","download_json":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D.json","view_paper":"https://pith.science/paper/QBFBEXOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00815&json=true","fetch_graph":"https://pith.science/api/pith-number/QBFBEXOED7TQC2H7UNFMOX7N6D/graph.json","fetch_events":"https://pith.science/api/pith-number/QBFBEXOED7TQC2H7UNFMOX7N6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D/action/storage_attestation","attest_author":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D/action/author_attestation","sign_citation":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D/action/citation_signature","submit_replication":"https://pith.science/pith/QBFBEXOED7TQC2H7UNFMOX7N6D/action/replication_record"}},"created_at":"2026-07-05T08:48:59.888642+00:00","updated_at":"2026-07-05T08:48:59.888642+00:00"}