{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HHQXMLQD4O7BLELPCVL4SKFNFX","short_pith_number":"pith:HHQXMLQD","schema_version":"1.0","canonical_sha256":"39e1762e03e3be15916f1557c928ad2dcea4c1dd7db6c2dce493b2ab4b591f15","source":{"kind":"arxiv","id":"2211.17121","version":1},"attestation_state":"computed","paper":{"title":"sEHR-CE: Language modelling of structured EHR data for efficient and generalizable patient cohort expansion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.AP"],"primary_cat":"cs.CL","authors_text":"Anna Munoz-Farre, Harry Rose, Sera Aylin Cakiroglu","submitted_at":"2022-11-30T16:00:43Z","abstract_excerpt":"Electronic health records (EHR) offer unprecedented opportunities for in-depth clinical phenotyping and prediction of clinical outcomes. Combining multiple data sources is crucial to generate a complete picture of disease prevalence, incidence and trajectories. The standard approach to combining clinical data involves collating clinical terms across different terminology systems using curated maps, which are often inaccurate and/or incomplete. Here, we propose sEHR-CE, a novel framework based on transformers to enable integrated phenotyping and analyses of heterogeneous clinical datasets witho"},"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":"2211.17121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-30T16:00:43Z","cross_cats_sorted":["cs.LG","stat.AP"],"title_canon_sha256":"cfbb447736e8a8c8e630e32221e6de0997ae6081f4ac4a505fdfe6d3df9241f1","abstract_canon_sha256":"37b4367f87b55d84f81e9dde1ce282635ed7ba69687c4f0a99721c626928e2f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:15.340892Z","signature_b64":"F+J3tKgTG58ZkATesRcN+3mvisk7foMnwnSYj7UI5Nn3tQp0M71NPhlBrRrTz2fGHaqC11aUd9o/7kJqvk0QCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39e1762e03e3be15916f1557c928ad2dcea4c1dd7db6c2dce493b2ab4b591f15","last_reissued_at":"2026-07-05T05:21:15.340462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:15.340462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"sEHR-CE: Language modelling of structured EHR data for efficient and generalizable patient cohort expansion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.AP"],"primary_cat":"cs.CL","authors_text":"Anna Munoz-Farre, Harry Rose, Sera Aylin Cakiroglu","submitted_at":"2022-11-30T16:00:43Z","abstract_excerpt":"Electronic health records (EHR) offer unprecedented opportunities for in-depth clinical phenotyping and prediction of clinical outcomes. Combining multiple data sources is crucial to generate a complete picture of disease prevalence, incidence and trajectories. The standard approach to combining clinical data involves collating clinical terms across different terminology systems using curated maps, which are often inaccurate and/or incomplete. Here, we propose sEHR-CE, a novel framework based on transformers to enable integrated phenotyping and analyses of heterogeneous clinical datasets witho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.17121","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/2211.17121/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":"2211.17121","created_at":"2026-07-05T05:21:15.340525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.17121v1","created_at":"2026-07-05T05:21:15.340525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.17121","created_at":"2026-07-05T05:21:15.340525+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHQXMLQD4O7B","created_at":"2026-07-05T05:21:15.340525+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHQXMLQD4O7BLELP","created_at":"2026-07-05T05:21:15.340525+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHQXMLQD","created_at":"2026-07-05T05:21:15.340525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01331","citing_title":"Exploring Long-Term Prediction of Type 2 Diabetes Microvascular Complications","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX","json":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX.json","graph_json":"https://pith.science/api/pith-number/HHQXMLQD4O7BLELPCVL4SKFNFX/graph.json","events_json":"https://pith.science/api/pith-number/HHQXMLQD4O7BLELPCVL4SKFNFX/events.json","paper":"https://pith.science/paper/HHQXMLQD"},"agent_actions":{"view_html":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX","download_json":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX.json","view_paper":"https://pith.science/paper/HHQXMLQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.17121&json=true","fetch_graph":"https://pith.science/api/pith-number/HHQXMLQD4O7BLELPCVL4SKFNFX/graph.json","fetch_events":"https://pith.science/api/pith-number/HHQXMLQD4O7BLELPCVL4SKFNFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX/action/storage_attestation","attest_author":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX/action/author_attestation","sign_citation":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX/action/citation_signature","submit_replication":"https://pith.science/pith/HHQXMLQD4O7BLELPCVL4SKFNFX/action/replication_record"}},"created_at":"2026-07-05T05:21:15.340525+00:00","updated_at":"2026-07-05T05:21:15.340525+00:00"}