{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RNK2EGQACESOAZM4KIQWYNHRP6","short_pith_number":"pith:RNK2EGQA","schema_version":"1.0","canonical_sha256":"8b55a21a001124e0659c52216c34f17faca67d281c93358b8edbd544300bff82","source":{"kind":"arxiv","id":"2301.03150","version":4},"attestation_state":"computed","paper":{"title":"MOTOR: A Time-To-Event Foundation Model For Structured Medical Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ethan Steinberg, Jason Fries, Nigam Shah, Yizhe Xu","submitted_at":"2023-01-09T02:42:39Z","abstract_excerpt":"We present a self-supervised, time-to-event (TTE) foundation model called MOTOR (Many Outcome Time Oriented Representations) which is pretrained on timestamped sequences of events in electronic health records (EHR) and health insurance claims. TTE models are used for estimating the probability distribution of the time until a specific event occurs, which is an important task in medical settings. TTE models provide many advantages over classification using fixed time horizons, including naturally handling censored observations, but are challenging to train with limited labeled data. MOTOR addre"},"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":"2301.03150","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-09T02:42:39Z","cross_cats_sorted":[],"title_canon_sha256":"e146ad063c6283754b9b1f68f4f21453ff21c2a385e262b92c68d81b0186f5e6","abstract_canon_sha256":"2436e819b4c00b5412b17c4d5d91ef597aeeb3d3dfc76f12b3a904746bff4b3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:06.740095Z","signature_b64":"IQ7IBvXDhMzcQ8I56y+nGg5hP+R/ke1c7CG4Dj0+QhYNKqDcdMmoyZtkcWlGbwHnWIhCb/+6x0igESMM2i6/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b55a21a001124e0659c52216c34f17faca67d281c93358b8edbd544300bff82","last_reissued_at":"2026-07-05T07:20:06.739606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:06.739606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOTOR: A Time-To-Event Foundation Model For Structured Medical Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ethan Steinberg, Jason Fries, Nigam Shah, Yizhe Xu","submitted_at":"2023-01-09T02:42:39Z","abstract_excerpt":"We present a self-supervised, time-to-event (TTE) foundation model called MOTOR (Many Outcome Time Oriented Representations) which is pretrained on timestamped sequences of events in electronic health records (EHR) and health insurance claims. TTE models are used for estimating the probability distribution of the time until a specific event occurs, which is an important task in medical settings. TTE models provide many advantages over classification using fixed time horizons, including naturally handling censored observations, but are challenging to train with limited labeled data. MOTOR addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03150","kind":"arxiv","version":4},"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/2301.03150/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":"2301.03150","created_at":"2026-07-05T07:20:06.739665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.03150v4","created_at":"2026-07-05T07:20:06.739665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03150","created_at":"2026-07-05T07:20:06.739665+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNK2EGQACESO","created_at":"2026-07-05T07:20:06.739665+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNK2EGQACESOAZM4","created_at":"2026-07-05T07:20:06.739665+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNK2EGQA","created_at":"2026-07-05T07:20:06.739665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.00520","citing_title":"NEST: Nested Event Stream Transformer for Sequences of Multisets","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14227","citing_title":"DT-Transformer: A Foundation Model for Disease Trajectory Prediction on a Real-world Health System","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04072","citing_title":"Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04071","citing_title":"FlatASCEND: Autoregressive Clinical Sequence Generation with Continuous Time Prediction and Association-Based Pharmacological Testing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16775","citing_title":"Representation Before Training: A Fixed-Budget Benchmark for Generative Medical Event Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02740","citing_title":"Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6","json":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6.json","graph_json":"https://pith.science/api/pith-number/RNK2EGQACESOAZM4KIQWYNHRP6/graph.json","events_json":"https://pith.science/api/pith-number/RNK2EGQACESOAZM4KIQWYNHRP6/events.json","paper":"https://pith.science/paper/RNK2EGQA"},"agent_actions":{"view_html":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6","download_json":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6.json","view_paper":"https://pith.science/paper/RNK2EGQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.03150&json=true","fetch_graph":"https://pith.science/api/pith-number/RNK2EGQACESOAZM4KIQWYNHRP6/graph.json","fetch_events":"https://pith.science/api/pith-number/RNK2EGQACESOAZM4KIQWYNHRP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6/action/storage_attestation","attest_author":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6/action/author_attestation","sign_citation":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6/action/citation_signature","submit_replication":"https://pith.science/pith/RNK2EGQACESOAZM4KIQWYNHRP6/action/replication_record"}},"created_at":"2026-07-05T07:20:06.739665+00:00","updated_at":"2026-07-05T07:20:06.739665+00:00"}