{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:74BQ66QKFNKLGVAHGWRXD6GJOH","short_pith_number":"pith:74BQ66QK","schema_version":"1.0","canonical_sha256":"ff030f7a0a2b54b3540735a371f8c971f320846d202dea383cb82c793e67f267","source":{"kind":"arxiv","id":"2604.01841","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Marie E. Ward, Marija Bezbradica, Martin Crane, Minh-Khoi Pham, Minh-Triet Tran, Nick McDonald, Rob Brennan, Tai Tan Mai, Thang-Long Nguyen Ho, Thao Thi Phuong Dao, Una Geary","submitted_at":"2026-04-02T09:56:17Z","abstract_excerpt":"Clinical prediction from structured electronic health records (EHRs) is challenging due to high dimensionality, heterogeneity, class imbalance, and distribution shift. While tabular in-context learning (TICL) and retrieval-augmented methods perform well on generic benchmarks, their behavior in clinical settings remains unclear. We present a multi-cohort EHR benchmark comparing classical, deep tabular, and TICL models across varying data scale, feature dimensionality, outcome rarity, and cross-cohort generalization. PFN-based TICL models are sample-efficient in low-data regimes but degrade unde"},"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":"2604.01841","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-02T09:56:17Z","cross_cats_sorted":[],"title_canon_sha256":"71e60ecf22cbdf337875a0ec1273beb29ba3006754276a5dab4452d11e2ed618","abstract_canon_sha256":"61e3d1096265e10dfbea0538e54b56f43ad1e06b37d71d3ca1fd5e82edc6a169"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:16.988159Z","signature_b64":"3MmO35W9eCxyzMtFMdmb+4UXsqgCrLqe+5GgWo4v3+hG9jHKOCcQ5eoQJyHFKimyzVTDmcCBZsAxxu4qq21yBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff030f7a0a2b54b3540735a371f8c971f320846d202dea383cb82c793e67f267","last_reissued_at":"2026-06-02T02:04:16.987678Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:16.987678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Marie E. Ward, Marija Bezbradica, Martin Crane, Minh-Khoi Pham, Minh-Triet Tran, Nick McDonald, Rob Brennan, Tai Tan Mai, Thang-Long Nguyen Ho, Thao Thi Phuong Dao, Una Geary","submitted_at":"2026-04-02T09:56:17Z","abstract_excerpt":"Clinical prediction from structured electronic health records (EHRs) is challenging due to high dimensionality, heterogeneity, class imbalance, and distribution shift. While tabular in-context learning (TICL) and retrieval-augmented methods perform well on generic benchmarks, their behavior in clinical settings remains unclear. We present a multi-cohort EHR benchmark comparing classical, deep tabular, and TICL models across varying data scale, feature dimensionality, outcome rarity, and cross-cohort generalization. PFN-based TICL models are sample-efficient in low-data regimes but degrade unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.01841","kind":"arxiv","version":2},"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/2604.01841/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":"2604.01841","created_at":"2026-06-02T02:04:16.987743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.01841v2","created_at":"2026-06-02T02:04:16.987743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.01841","created_at":"2026-06-02T02:04:16.987743+00:00"},{"alias_kind":"pith_short_12","alias_value":"74BQ66QKFNKL","created_at":"2026-06-02T02:04:16.987743+00:00"},{"alias_kind":"pith_short_16","alias_value":"74BQ66QKFNKLGVAH","created_at":"2026-06-02T02:04:16.987743+00:00"},{"alias_kind":"pith_short_8","alias_value":"74BQ66QK","created_at":"2026-06-02T02:04:16.987743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.12006","citing_title":"Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH","json":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH.json","graph_json":"https://pith.science/api/pith-number/74BQ66QKFNKLGVAHGWRXD6GJOH/graph.json","events_json":"https://pith.science/api/pith-number/74BQ66QKFNKLGVAHGWRXD6GJOH/events.json","paper":"https://pith.science/paper/74BQ66QK"},"agent_actions":{"view_html":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH","download_json":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH.json","view_paper":"https://pith.science/paper/74BQ66QK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.01841&json=true","fetch_graph":"https://pith.science/api/pith-number/74BQ66QKFNKLGVAHGWRXD6GJOH/graph.json","fetch_events":"https://pith.science/api/pith-number/74BQ66QKFNKLGVAHGWRXD6GJOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH/action/storage_attestation","attest_author":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH/action/author_attestation","sign_citation":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH/action/citation_signature","submit_replication":"https://pith.science/pith/74BQ66QKFNKLGVAHGWRXD6GJOH/action/replication_record"}},"created_at":"2026-06-02T02:04:16.987743+00:00","updated_at":"2026-06-02T02:04:16.987743+00:00"}