{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4OTGHUXZRJ7UEEDYQQCS3ZX45V","short_pith_number":"pith:4OTGHUXZ","schema_version":"1.0","canonical_sha256":"e3a663d2f98a7f42107884052de6fced5469f627e58326c509c8271f258b6648","source":{"kind":"arxiv","id":"2407.07110","version":3},"attestation_state":"computed","paper":{"title":"CREMA: A Contrastive Regularized Masked Autoencoder for Robust ECG Diagnostics across Clinical Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Donggyun Hong, Jong-Hwan Jang, Joon-myoung Kwon, Junho Song, Yong-yeon Jo","submitted_at":"2024-06-26T02:24:13Z","abstract_excerpt":"Electrocardiogram (ECG) diagnosis remains challenging due to limited labeled data and the need to capture subtle yet clinically meaningful variations in rhythm and morphology. We present CREMA (Contrastive Regularized Masked Autoencoder), a foundation model for 12-lead ECGs designed to learn generalizable representations through self-supervised pretraining. CREMA combines generative learning and contrastive regularization via a Contrastive Regularized MAE loss, and employs a Signal Transformer (SiT) architecture to capture both local waveform details and global temporal dependencies. We evalua"},"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":"2407.07110","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T02:24:13Z","cross_cats_sorted":["cs.AI","eess.SP"],"title_canon_sha256":"7c009ca627375b504445d244508158c4a6ada7cac8fd5182061cf47b537373b1","abstract_canon_sha256":"30d5ed2b661f46c1965463c40e8d085d30c90fcb85447a81b0a615fc46fc2e0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:49.043365Z","signature_b64":"1ptQkQbnbxePg+wpwk1TA0GX9Nps/Xi8UtOD6UvTGOoP9kuDoGsbtc3eEGJSBuiuFvr972mNtZUQ/3hdrKCWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3a663d2f98a7f42107884052de6fced5469f627e58326c509c8271f258b6648","last_reissued_at":"2026-07-05T11:56:49.042580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:49.042580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CREMA: A Contrastive Regularized Masked Autoencoder for Robust ECG Diagnostics across Clinical Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Donggyun Hong, Jong-Hwan Jang, Joon-myoung Kwon, Junho Song, Yong-yeon Jo","submitted_at":"2024-06-26T02:24:13Z","abstract_excerpt":"Electrocardiogram (ECG) diagnosis remains challenging due to limited labeled data and the need to capture subtle yet clinically meaningful variations in rhythm and morphology. We present CREMA (Contrastive Regularized Masked Autoencoder), a foundation model for 12-lead ECGs designed to learn generalizable representations through self-supervised pretraining. CREMA combines generative learning and contrastive regularization via a Contrastive Regularized MAE loss, and employs a Signal Transformer (SiT) architecture to capture both local waveform details and global temporal dependencies. We evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07110","kind":"arxiv","version":3},"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/2407.07110/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":"2407.07110","created_at":"2026-07-05T11:56:49.042683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07110v3","created_at":"2026-07-05T11:56:49.042683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07110","created_at":"2026-07-05T11:56:49.042683+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OTGHUXZRJ7U","created_at":"2026-07-05T11:56:49.042683+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OTGHUXZRJ7UEEDY","created_at":"2026-07-05T11:56:49.042683+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OTGHUXZ","created_at":"2026-07-05T11:56:49.042683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16975","citing_title":"Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V","json":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V.json","graph_json":"https://pith.science/api/pith-number/4OTGHUXZRJ7UEEDYQQCS3ZX45V/graph.json","events_json":"https://pith.science/api/pith-number/4OTGHUXZRJ7UEEDYQQCS3ZX45V/events.json","paper":"https://pith.science/paper/4OTGHUXZ"},"agent_actions":{"view_html":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V","download_json":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V.json","view_paper":"https://pith.science/paper/4OTGHUXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07110&json=true","fetch_graph":"https://pith.science/api/pith-number/4OTGHUXZRJ7UEEDYQQCS3ZX45V/graph.json","fetch_events":"https://pith.science/api/pith-number/4OTGHUXZRJ7UEEDYQQCS3ZX45V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V/action/storage_attestation","attest_author":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V/action/author_attestation","sign_citation":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V/action/citation_signature","submit_replication":"https://pith.science/pith/4OTGHUXZRJ7UEEDYQQCS3ZX45V/action/replication_record"}},"created_at":"2026-07-05T11:56:49.042683+00:00","updated_at":"2026-07-05T11:56:49.042683+00:00"}