{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:43LALAI6K4ERVRE7UEF3MOIKP7","short_pith_number":"pith:43LALAI6","schema_version":"1.0","canonical_sha256":"e6d605811e57091ac49fa10bb6390a7fe65eb8d02fae71269e85b84bb042dedb","source":{"kind":"arxiv","id":"2507.18583","version":1},"attestation_state":"computed","paper":{"title":"DR.EHR: Dense Retrieval for Electronic Health Record with Knowledge Injection and Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Huaiyuan Ying, Sheng Yu, Yue Zhong, Zhengyun Zhao","submitted_at":"2025-07-24T17:02:46Z","abstract_excerpt":"Electronic Health Records (EHRs) are pivotal in clinical practices, yet their retrieval remains a challenge mainly due to semantic gap issues. Recent advancements in dense retrieval offer promising solutions but existing models, both general-domain and biomedical-domain, fall short due to insufficient medical knowledge or mismatched training corpora. This paper introduces \\texttt{DR.EHR}, a series of dense retrieval models specifically tailored for EHR retrieval. We propose a two-stage training pipeline utilizing MIMIC-IV discharge summaries to address the need for extensive medical knowledge "},"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":"2507.18583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-24T17:02:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b103934ba2d94c72c96e779543c6c9f4fcbb4b62c191a5d1d273e3210ecc34e8","abstract_canon_sha256":"eecae5e90aad75e46482bb853ebe5be960b9a38aea101389686e940c1296ea52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:50.408517Z","signature_b64":"pBsPXlMsuKttjkoCd8I8LOgRxlvJxixX0H5ch2Svmr9LIjcDdR4lqyF9LMSVcPh71EeKnBQSEPZHi+jEd7/jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6d605811e57091ac49fa10bb6390a7fe65eb8d02fae71269e85b84bb042dedb","last_reissued_at":"2026-07-05T11:42:50.408055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:50.408055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DR.EHR: Dense Retrieval for Electronic Health Record with Knowledge Injection and Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Huaiyuan Ying, Sheng Yu, Yue Zhong, Zhengyun Zhao","submitted_at":"2025-07-24T17:02:46Z","abstract_excerpt":"Electronic Health Records (EHRs) are pivotal in clinical practices, yet their retrieval remains a challenge mainly due to semantic gap issues. Recent advancements in dense retrieval offer promising solutions but existing models, both general-domain and biomedical-domain, fall short due to insufficient medical knowledge or mismatched training corpora. This paper introduces \\texttt{DR.EHR}, a series of dense retrieval models specifically tailored for EHR retrieval. We propose a two-stage training pipeline utilizing MIMIC-IV discharge summaries to address the need for extensive medical knowledge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18583","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/2507.18583/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":"2507.18583","created_at":"2026-07-05T11:42:50.408109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18583v1","created_at":"2026-07-05T11:42:50.408109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18583","created_at":"2026-07-05T11:42:50.408109+00:00"},{"alias_kind":"pith_short_12","alias_value":"43LALAI6K4ER","created_at":"2026-07-05T11:42:50.408109+00:00"},{"alias_kind":"pith_short_16","alias_value":"43LALAI6K4ERVRE7","created_at":"2026-07-05T11:42:50.408109+00:00"},{"alias_kind":"pith_short_8","alias_value":"43LALAI6","created_at":"2026-07-05T11:42:50.408109+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":166,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7","json":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7.json","graph_json":"https://pith.science/api/pith-number/43LALAI6K4ERVRE7UEF3MOIKP7/graph.json","events_json":"https://pith.science/api/pith-number/43LALAI6K4ERVRE7UEF3MOIKP7/events.json","paper":"https://pith.science/paper/43LALAI6"},"agent_actions":{"view_html":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7","download_json":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7.json","view_paper":"https://pith.science/paper/43LALAI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18583&json=true","fetch_graph":"https://pith.science/api/pith-number/43LALAI6K4ERVRE7UEF3MOIKP7/graph.json","fetch_events":"https://pith.science/api/pith-number/43LALAI6K4ERVRE7UEF3MOIKP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7/action/storage_attestation","attest_author":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7/action/author_attestation","sign_citation":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7/action/citation_signature","submit_replication":"https://pith.science/pith/43LALAI6K4ERVRE7UEF3MOIKP7/action/replication_record"}},"created_at":"2026-07-05T11:42:50.408109+00:00","updated_at":"2026-07-05T11:42:50.408109+00:00"}