{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2FSY3E3AZO5RREHE4YZYNSNVIA","short_pith_number":"pith:2FSY3E3A","schema_version":"1.0","canonical_sha256":"d1658d9360cbbb1890e4e63386c9b54016373ee9820af6e0a6c790ea09f0ddb0","source":{"kind":"arxiv","id":"2411.00200","version":1},"attestation_state":"computed","paper":{"title":"MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksia Kolo, Collin M. Stultz, Hanna Gaggin, Hyewon Jeong, Matthew B.A. McDermott, Nassim Oufattole, Teya Bergamaschi","submitted_at":"2024-10-31T20:36:37Z","abstract_excerpt":"Effective, reliable, and scalable development of machine learning (ML) solutions for structured electronic health record (EHR) data requires the ability to reliably generate high-quality baseline models for diverse supervised learning tasks in an efficient and performant manner. Historically, producing such baseline models has been a largely manual effort--individual researchers would need to decide on the particular featurization and tabularization processes to apply to their individual raw, longitudinal data; and then train a supervised model over those data to produce a baseline result to c"},"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":"2411.00200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T20:36:37Z","cross_cats_sorted":[],"title_canon_sha256":"b6d6d1b52abff1c7275adb361544a33af0ed0abdf7f634d39ef3e96877cefb45","abstract_canon_sha256":"6ff152d3aef973663746752a17604b698a505df91b4230ad398c29b07b1bbef1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:39.186912Z","signature_b64":"sM3czYoq2Ehl48MecyHUeRfjmSSrulhukXSQEBIcvi6ny0lukFjEzZrk5bSSXmeqoC2VZMTD62+rmk6Og7tlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1658d9360cbbb1890e4e63386c9b54016373ee9820af6e0a6c790ea09f0ddb0","last_reissued_at":"2026-07-05T09:29:39.186397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:39.186397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksia Kolo, Collin M. Stultz, Hanna Gaggin, Hyewon Jeong, Matthew B.A. McDermott, Nassim Oufattole, Teya Bergamaschi","submitted_at":"2024-10-31T20:36:37Z","abstract_excerpt":"Effective, reliable, and scalable development of machine learning (ML) solutions for structured electronic health record (EHR) data requires the ability to reliably generate high-quality baseline models for diverse supervised learning tasks in an efficient and performant manner. Historically, producing such baseline models has been a largely manual effort--individual researchers would need to decide on the particular featurization and tabularization processes to apply to their individual raw, longitudinal data; and then train a supervised model over those data to produce a baseline result to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00200","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/2411.00200/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":"2411.00200","created_at":"2026-07-05T09:29:39.186449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00200v1","created_at":"2026-07-05T09:29:39.186449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00200","created_at":"2026-07-05T09:29:39.186449+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FSY3E3AZO5R","created_at":"2026-07-05T09:29:39.186449+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FSY3E3AZO5RREHE","created_at":"2026-07-05T09:29:39.186449+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FSY3E3A","created_at":"2026-07-05T09:29:39.186449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16941","citing_title":"FoMoH: A clinically meaningful foundation model evaluation for structured electronic health records","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA","json":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA.json","graph_json":"https://pith.science/api/pith-number/2FSY3E3AZO5RREHE4YZYNSNVIA/graph.json","events_json":"https://pith.science/api/pith-number/2FSY3E3AZO5RREHE4YZYNSNVIA/events.json","paper":"https://pith.science/paper/2FSY3E3A"},"agent_actions":{"view_html":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA","download_json":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA.json","view_paper":"https://pith.science/paper/2FSY3E3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00200&json=true","fetch_graph":"https://pith.science/api/pith-number/2FSY3E3AZO5RREHE4YZYNSNVIA/graph.json","fetch_events":"https://pith.science/api/pith-number/2FSY3E3AZO5RREHE4YZYNSNVIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA/action/storage_attestation","attest_author":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA/action/author_attestation","sign_citation":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA/action/citation_signature","submit_replication":"https://pith.science/pith/2FSY3E3AZO5RREHE4YZYNSNVIA/action/replication_record"}},"created_at":"2026-07-05T09:29:39.186449+00:00","updated_at":"2026-07-05T09:29:39.186449+00:00"}