{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IBZQX3XUPKHOXSF4UN7XCHIQ7M","short_pith_number":"pith:IBZQX3XU","schema_version":"1.0","canonical_sha256":"40730beef47a8eebc8bca37f711d10fb34b1ff844cacebfe25202b5d0a36cf70","source":{"kind":"arxiv","id":"2410.03794","version":2},"attestation_state":"computed","paper":{"title":"Repurposing Foundation Model for Generalizable Medical Time Series Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haishuai Wang, Marinka Zitnik, Nan Huang, Xiang Zhang, Zihuai He","submitted_at":"2024-10-03T23:50:04Z","abstract_excerpt":"Medical time series (MedTS) classification suffers from poor generalizability in real-world deployment due to inter- and intra-dataset heterogeneity, such as varying numbers of channels, signal lengths, task definitions, and patient characteristics. To address this, we propose FORMED, a novel framework for repurposing a backbone foundation model, pre-trained on generic time series, to enable highly generalizable MedTS classification on unseen datasets. FORMED combines the backbone with a novel classifier comprising two components: (1) task-specific channel embeddings and label queries, dynamic"},"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":"2410.03794","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T23:50:04Z","cross_cats_sorted":[],"title_canon_sha256":"e72a04ad0818bf9239f8ea7a06208df5b61d7f4336bf48fd4a6e3c85a6c44ae3","abstract_canon_sha256":"6764096589c4f209f44606bb463c09f5b784f23834f4b3b11c0793575c6e7df9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:21.704889Z","signature_b64":"+DQ/shD63Xu+8FMpPBFm6QkyFFJriC2ol8m0MahTbEHabDP8wR/6mEBGTSPY/sRoiiPbIMNJ1O51TLY7OA4CBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40730beef47a8eebc8bca37f711d10fb34b1ff844cacebfe25202b5d0a36cf70","last_reissued_at":"2026-07-05T11:05:21.704442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:21.704442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repurposing Foundation Model for Generalizable Medical Time Series Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haishuai Wang, Marinka Zitnik, Nan Huang, Xiang Zhang, Zihuai He","submitted_at":"2024-10-03T23:50:04Z","abstract_excerpt":"Medical time series (MedTS) classification suffers from poor generalizability in real-world deployment due to inter- and intra-dataset heterogeneity, such as varying numbers of channels, signal lengths, task definitions, and patient characteristics. To address this, we propose FORMED, a novel framework for repurposing a backbone foundation model, pre-trained on generic time series, to enable highly generalizable MedTS classification on unseen datasets. FORMED combines the backbone with a novel classifier comprising two components: (1) task-specific channel embeddings and label queries, dynamic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03794","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/2410.03794/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":"2410.03794","created_at":"2026-07-05T11:05:21.704497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03794v2","created_at":"2026-07-05T11:05:21.704497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03794","created_at":"2026-07-05T11:05:21.704497+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBZQX3XUPKHO","created_at":"2026-07-05T11:05:21.704497+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBZQX3XUPKHOXSF4","created_at":"2026-07-05T11:05:21.704497+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBZQX3XU","created_at":"2026-07-05T11:05:21.704497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09643","citing_title":"FMplex: Model Virtualization for Serving Extensible Foundation Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00573","citing_title":"Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M","json":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M.json","graph_json":"https://pith.science/api/pith-number/IBZQX3XUPKHOXSF4UN7XCHIQ7M/graph.json","events_json":"https://pith.science/api/pith-number/IBZQX3XUPKHOXSF4UN7XCHIQ7M/events.json","paper":"https://pith.science/paper/IBZQX3XU"},"agent_actions":{"view_html":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M","download_json":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M.json","view_paper":"https://pith.science/paper/IBZQX3XU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03794&json=true","fetch_graph":"https://pith.science/api/pith-number/IBZQX3XUPKHOXSF4UN7XCHIQ7M/graph.json","fetch_events":"https://pith.science/api/pith-number/IBZQX3XUPKHOXSF4UN7XCHIQ7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M/action/storage_attestation","attest_author":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M/action/author_attestation","sign_citation":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M/action/citation_signature","submit_replication":"https://pith.science/pith/IBZQX3XUPKHOXSF4UN7XCHIQ7M/action/replication_record"}},"created_at":"2026-07-05T11:05:21.704497+00:00","updated_at":"2026-07-05T11:05:21.704497+00:00"}