{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LBWCSO2CJZFXXXIWF6KHLSEM74","short_pith_number":"pith:LBWCSO2C","schema_version":"1.0","canonical_sha256":"586c293b424e4b7bdd162f9475c88cff2bfb422b7a507f8e098172cc65ab2d9b","source":{"kind":"arxiv","id":"2512.21602","version":3},"attestation_state":"computed","paper":{"title":"An Empirical Study of Machine Learning Robustness and Scalability for Imbalanced Tabular Clinical Data in Emergency and Critical Care","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Tabular foundation models achieve competitive results on imbalanced clinical data at lower computational cost than deeper alternatives.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Marcellin Atemkeng, Yusuf Brima","submitted_at":"2025-12-25T09:49:48Z","abstract_excerpt":"Every year, millions of patients pass through emergency departments and intensive care units, where clinicians must make high-stakes decisions under time pressure and uncertainty. Machine learning could support prediction of deterioration, triage, and rare critical outcomes, but clinical data are often severely imbalanced, biasing models toward majority classes and reducing predictive performance. Developing robust and efficient models for imbalanced clinical tabular data therefore remains an important challenge.\n  We evaluated six model families on imbalanced tabular data from the MIMIC-IV-ED"},"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":"2512.21602","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-25T09:49:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a6a4bff74efa7438e662da4320d3fd96107295b52dd7ee46f67d175d94ca4ef7","abstract_canon_sha256":"49268615cffbe5c95ee3c8a6cf19f1086b64bac297bf7bae9cf858e8ef932ff4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:54.194706Z","signature_b64":"EA0UhAZc3q3Ea4KoPnhJ63P5sXPyuDH/nGiKctAkV5hMDyzMqYt3fXfVGP5KGonTgoo/O0fWfQiQ9a4PHwGICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586c293b424e4b7bdd162f9475c88cff2bfb422b7a507f8e098172cc65ab2d9b","last_reissued_at":"2026-05-27T01:04:54.194076Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:54.194076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of Machine Learning Robustness and Scalability for Imbalanced Tabular Clinical Data in Emergency and Critical Care","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Tabular foundation models achieve competitive results on imbalanced clinical data at lower computational cost than deeper alternatives.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Marcellin Atemkeng, Yusuf Brima","submitted_at":"2025-12-25T09:49:48Z","abstract_excerpt":"Every year, millions of patients pass through emergency departments and intensive care units, where clinicians must make high-stakes decisions under time pressure and uncertainty. Machine learning could support prediction of deterioration, triage, and rare critical outcomes, but clinical data are often severely imbalanced, biasing models toward majority classes and reducing predictive performance. Developing robust and efficient models for imbalanced clinical tabular data therefore remains an important challenge.\n  We evaluated six model families on imbalanced tabular data from the MIMIC-IV-ED"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Tabular foundation models showed promise by combining competitive performance at low computational cost.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the two chosen datasets and seven prediction tasks sufficiently represent real-world clinical imbalance scenarios and that results will generalize beyond MIMIC-IV-ED and eICU.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Tabular foundation models achieve competitive weighted F1 scores on imbalanced emergency care data while scaling more efficiently than some deep models like TabNet.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Tabular foundation models achieve competitive results on imbalanced clinical data at lower computational cost than deeper alternatives.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"957d2e08a75b1ed76dc0744017711fc9e14f8315ab55a261e6804242cb593ecf"},"source":{"id":"2512.21602","kind":"arxiv","version":3},"verdict":{"id":"3e3c671a-74f4-451d-9fa1-e8a1f2f60fef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T19:42:31.172015Z","strongest_claim":"Tabular foundation models showed promise by combining competitive performance at low computational cost.","one_line_summary":"Tabular foundation models achieve competitive weighted F1 scores on imbalanced emergency care data while scaling more efficiently than some deep models like TabNet.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the two chosen datasets and seven prediction tasks sufficiently represent real-world clinical imbalance scenarios and that results will generalize beyond MIMIC-IV-ED and eICU.","pith_extraction_headline":"Tabular foundation models achieve competitive results on imbalanced clinical data at lower computational cost than deeper alternatives."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.21602/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":"2512.21602","created_at":"2026-05-27T01:04:54.194157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.21602v3","created_at":"2026-05-27T01:04:54.194157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.21602","created_at":"2026-05-27T01:04:54.194157+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBWCSO2CJZFX","created_at":"2026-05-27T01:04:54.194157+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBWCSO2CJZFXXXIW","created_at":"2026-05-27T01:04:54.194157+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBWCSO2C","created_at":"2026-05-27T01:04:54.194157+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/LBWCSO2CJZFXXXIWF6KHLSEM74","json":"https://pith.science/pith/LBWCSO2CJZFXXXIWF6KHLSEM74.json","graph_json":"https://pith.science/api/pith-number/LBWCSO2CJZFXXXIWF6KHLSEM74/graph.json","events_json":"https://pith.science/api/pith-number/LBWCSO2CJZFXXXIWF6KHLSEM74/events.json","paper":"https://pith.science/paper/LBWCSO2C"},"agent_actions":{"view_html":"https://pith.science/pith/LBWCSO2CJZFXXXIWF6KHLSEM74","download_json":"https://pith.science/pith/LBWCSO2CJZFXXXIWF6KHLSEM74.json","view_paper":"https://pith.science/paper/LBWCSO2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.21602&json=true","fetch_graph":"https://pith.science/api/pith-number/LBWCSO2CJZFXXXIWF6KHLSEM74/graph.json","fetch_events":"https://pith.science/api/pith-number/LBWCSO2CJZFXXXIWF6KHLSEM74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBWCSO2CJZFXXXIWF6KHLSEM74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBWCSO2CJZFXXXIWF6KHLSEM74/action/storage_attestation","attest_author":"https://pith.science/pith/LBWCSO2CJZFXXXIWF6KHLSEM74/action/author_attestation","sign_citation":"https://pith.science/pith/LBWCSO2CJZFXXXIWF6KHLSEM74/action/citation_signature","submit_replication":"https://pith.science/pith/LBWCSO2CJZFXXXIWF6KHLSEM74/action/replication_record"}},"created_at":"2026-05-27T01:04:54.194157+00:00","updated_at":"2026-05-27T01:04:54.194157+00:00"}