{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EMWBO7MATCZSTQPQV37F74QCD4","short_pith_number":"pith:EMWBO7MA","schema_version":"1.0","canonical_sha256":"232c177d8098b329c1f0aefe5ff2021f31dd601b8d173ee7c8f69618563fb03f","source":{"kind":"arxiv","id":"2607.06163","version":1},"attestation_state":"computed","paper":{"title":"X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Capurro, Jie Huang, Mike Conway, Pengfei Yin, Ting Dang, Zihan Xu","submitted_at":"2026-07-07T11:37:43Z","abstract_excerpt":"Foundation Models for Electronic Health Records (FEMRs) are pretrained on large-scale structured patient data, enabling them to convert longitudinal patient trajectories into generalizable representations for diverse clinical prediction tasks. Despite their effectiveness, FEMRs remain black-box models, raising concerns about bias, interpretability, and clinical trust. To address this, we propose the first token-level explainability approach for FEMRs. We train a Transformer-based surrogate model on input-output pairs from the FEMR across two prediction tasks, approximating its behavior while p"},"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":"2607.06163","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T11:37:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af9b98b826cd43013cceb6ef25ce85dd276ec13a3f4005907347d98eef10e64c","abstract_canon_sha256":"a6daba6e7ef15aa06ea03cb22fc927bdb2c701e02527ae655aabd7c91aeacfc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:58.918489Z","signature_b64":"shQ3wOov7pJHcR2YGurUI/w+6vxdybF+HnpMgG/9+zgVcVX2OW2qhotqCyMjkZFAsxlisEdNW/ntF49F91LZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"232c177d8098b329c1f0aefe5ff2021f31dd601b8d173ee7c8f69618563fb03f","last_reissued_at":"2026-07-08T01:18:58.918023Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:58.918023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Capurro, Jie Huang, Mike Conway, Pengfei Yin, Ting Dang, Zihan Xu","submitted_at":"2026-07-07T11:37:43Z","abstract_excerpt":"Foundation Models for Electronic Health Records (FEMRs) are pretrained on large-scale structured patient data, enabling them to convert longitudinal patient trajectories into generalizable representations for diverse clinical prediction tasks. Despite their effectiveness, FEMRs remain black-box models, raising concerns about bias, interpretability, and clinical trust. To address this, we propose the first token-level explainability approach for FEMRs. We train a Transformer-based surrogate model on input-output pairs from the FEMR across two prediction tasks, approximating its behavior while p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06163","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/2607.06163/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":"2607.06163","created_at":"2026-07-08T01:18:58.918091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06163v1","created_at":"2026-07-08T01:18:58.918091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06163","created_at":"2026-07-08T01:18:58.918091+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMWBO7MATCZS","created_at":"2026-07-08T01:18:58.918091+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMWBO7MATCZSTQPQ","created_at":"2026-07-08T01:18:58.918091+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMWBO7MA","created_at":"2026-07-08T01:18:58.918091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4","json":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4.json","graph_json":"https://pith.science/api/pith-number/EMWBO7MATCZSTQPQV37F74QCD4/graph.json","events_json":"https://pith.science/api/pith-number/EMWBO7MATCZSTQPQV37F74QCD4/events.json","paper":"https://pith.science/paper/EMWBO7MA"},"agent_actions":{"view_html":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4","download_json":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4.json","view_paper":"https://pith.science/paper/EMWBO7MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06163&json=true","fetch_graph":"https://pith.science/api/pith-number/EMWBO7MATCZSTQPQV37F74QCD4/graph.json","fetch_events":"https://pith.science/api/pith-number/EMWBO7MATCZSTQPQV37F74QCD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4/action/storage_attestation","attest_author":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4/action/author_attestation","sign_citation":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4/action/citation_signature","submit_replication":"https://pith.science/pith/EMWBO7MATCZSTQPQV37F74QCD4/action/replication_record"}},"created_at":"2026-07-08T01:18:58.918091+00:00","updated_at":"2026-07-08T01:18:58.918091+00:00"}