{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:25OREWG32SGC6U3RNI2UTJQ5JE","short_pith_number":"pith:25OREWG3","schema_version":"1.0","canonical_sha256":"d75d1258dbd48c2f53716a3549a61d493e9dba8e62d6fcd420ba9e6ba8781c15","source":{"kind":"arxiv","id":"2505.17643","version":1},"attestation_state":"computed","paper":{"title":"Bridging Electronic Health Records and Clinical Texts: Contrastive Learning for Enhanced Clinical Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dhanesh Ramachandram, Sara Ketabi","submitted_at":"2025-05-23T09:04:49Z","abstract_excerpt":"Conventional machine learning models, particularly tree-based approaches, have demonstrated promising performance across various clinical prediction tasks using electronic health record (EHR) data. Despite their strengths, these models struggle with tasks that require deeper contextual understanding, such as predicting 30-day hospital readmission. This can be primarily due to the limited semantic information available in structured EHR data. To address this limitation, we propose a deep multimodal contrastive learning (CL) framework that aligns the latent representations of structured EHR data"},"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":"2505.17643","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:04:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b852b658ba8a75a9345abc8b2715ded5167a769c3c22837443164bc6cc296e64","abstract_canon_sha256":"2959d4b83130d00d11797ee2fe4ea40964b6956b7a69572babea8c9662a55faf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:29.832203Z","signature_b64":"2vRa4cuRrQwfvJOI2K4gXbH6DGua/pVsmpNo9/hO6Y8UXiCiKSNcUYDleUKsTYUBQ7RYd39vlLcoYEBay6KdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d75d1258dbd48c2f53716a3549a61d493e9dba8e62d6fcd420ba9e6ba8781c15","last_reissued_at":"2026-07-05T11:08:29.831761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:29.831761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Electronic Health Records and Clinical Texts: Contrastive Learning for Enhanced Clinical Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dhanesh Ramachandram, Sara Ketabi","submitted_at":"2025-05-23T09:04:49Z","abstract_excerpt":"Conventional machine learning models, particularly tree-based approaches, have demonstrated promising performance across various clinical prediction tasks using electronic health record (EHR) data. Despite their strengths, these models struggle with tasks that require deeper contextual understanding, such as predicting 30-day hospital readmission. This can be primarily due to the limited semantic information available in structured EHR data. To address this limitation, we propose a deep multimodal contrastive learning (CL) framework that aligns the latent representations of structured EHR data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17643","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/2505.17643/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":"2505.17643","created_at":"2026-07-05T11:08:29.831818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17643v1","created_at":"2026-07-05T11:08:29.831818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17643","created_at":"2026-07-05T11:08:29.831818+00:00"},{"alias_kind":"pith_short_12","alias_value":"25OREWG32SGC","created_at":"2026-07-05T11:08:29.831818+00:00"},{"alias_kind":"pith_short_16","alias_value":"25OREWG32SGC6U3R","created_at":"2026-07-05T11:08:29.831818+00:00"},{"alias_kind":"pith_short_8","alias_value":"25OREWG3","created_at":"2026-07-05T11:08:29.831818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16878","citing_title":"OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE","json":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE.json","graph_json":"https://pith.science/api/pith-number/25OREWG32SGC6U3RNI2UTJQ5JE/graph.json","events_json":"https://pith.science/api/pith-number/25OREWG32SGC6U3RNI2UTJQ5JE/events.json","paper":"https://pith.science/paper/25OREWG3"},"agent_actions":{"view_html":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE","download_json":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE.json","view_paper":"https://pith.science/paper/25OREWG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17643&json=true","fetch_graph":"https://pith.science/api/pith-number/25OREWG32SGC6U3RNI2UTJQ5JE/graph.json","fetch_events":"https://pith.science/api/pith-number/25OREWG32SGC6U3RNI2UTJQ5JE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE/action/storage_attestation","attest_author":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE/action/author_attestation","sign_citation":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE/action/citation_signature","submit_replication":"https://pith.science/pith/25OREWG32SGC6U3RNI2UTJQ5JE/action/replication_record"}},"created_at":"2026-07-05T11:08:29.831818+00:00","updated_at":"2026-07-05T11:08:29.831818+00:00"}