{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7Q3IGBH6AHTWTR3PM3EY37CYNT","short_pith_number":"pith:7Q3IGBH6","schema_version":"1.0","canonical_sha256":"fc368304fe01e769c76f66c98dfc586ce22b0a1dd60b98bf6d46ec8cf8054566","source":{"kind":"arxiv","id":"2408.05178","version":2},"attestation_state":"computed","paper":{"title":"ECG-FM: An Open Electrocardiogram Foundation Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Augustin Toma, Barry Rubin, Bo Wang, Kaden McKeen, Sameer Masood","submitted_at":"2024-08-09T17:06:49Z","abstract_excerpt":"Conventional task-specific electrocardiogram (ECG) analysis models require large annotated datasets to train. Foundation models mitigate this burden by leveraging self-supervised pretraining; however, the scarcity of open-weight ECG foundation models hinders adoption and cross-study comparability. We present ECG-FM, an open foundation model for ECG analysis, and conduct a study using a dataset of 1.5 million ECGs. ECG-FM is a transformer-based model pretrained using a hybrid contrastive and generative self-supervised learning approach. Our downstream tasks include predicting reduced left ventr"},"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":"2408.05178","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T17:06:49Z","cross_cats_sorted":[],"title_canon_sha256":"349e5f0d13400cf973445c79124545bf342097d525209986679a89ebbe671cae","abstract_canon_sha256":"85ef6295309a66ead6c3ec14db682042b6e5ba39199daf204f37a83206f58ac6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:19.074207Z","signature_b64":"vSk1ELlYxqOk06eHcK/OxsRf0qdSZrFJZ5tCQAjPEdKNDBZ+aE6rF2xQgygyRbSEsgelhSd0ibPxqSeBsP2cAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc368304fe01e769c76f66c98dfc586ce22b0a1dd60b98bf6d46ec8cf8054566","last_reissued_at":"2026-07-05T11:12:19.073703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:19.073703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECG-FM: An Open Electrocardiogram Foundation Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Augustin Toma, Barry Rubin, Bo Wang, Kaden McKeen, Sameer Masood","submitted_at":"2024-08-09T17:06:49Z","abstract_excerpt":"Conventional task-specific electrocardiogram (ECG) analysis models require large annotated datasets to train. Foundation models mitigate this burden by leveraging self-supervised pretraining; however, the scarcity of open-weight ECG foundation models hinders adoption and cross-study comparability. We present ECG-FM, an open foundation model for ECG analysis, and conduct a study using a dataset of 1.5 million ECGs. ECG-FM is a transformer-based model pretrained using a hybrid contrastive and generative self-supervised learning approach. Our downstream tasks include predicting reduced left ventr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05178","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/2408.05178/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":"2408.05178","created_at":"2026-07-05T11:12:19.073763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05178v2","created_at":"2026-07-05T11:12:19.073763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05178","created_at":"2026-07-05T11:12:19.073763+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q3IGBH6AHTW","created_at":"2026-07-05T11:12:19.073763+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q3IGBH6AHTWTR3P","created_at":"2026-07-05T11:12:19.073763+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q3IGBH6","created_at":"2026-07-05T11:12:19.073763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17276","citing_title":"How Do Electrocardiogram Models Scale?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15465","citing_title":"Toward World Modeling of Physiological Signals with Chaos-Theoretic Balancing and Latent Dynamics","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02501","citing_title":"ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09579","citing_title":"Biosignal Fingerprinting: A Cross-Modal PPG-ECG Foundation Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09848","citing_title":"Efficient Neural Architectures for Real-Time ECG Interpretation on Limited Hardware","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10172","citing_title":"Wearable AI in the Era of Large Sensor Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18067","citing_title":"Towards Real-Time ECG and EMG Modeling on $\\mu$NPUs","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT","json":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT.json","graph_json":"https://pith.science/api/pith-number/7Q3IGBH6AHTWTR3PM3EY37CYNT/graph.json","events_json":"https://pith.science/api/pith-number/7Q3IGBH6AHTWTR3PM3EY37CYNT/events.json","paper":"https://pith.science/paper/7Q3IGBH6"},"agent_actions":{"view_html":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT","download_json":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT.json","view_paper":"https://pith.science/paper/7Q3IGBH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05178&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q3IGBH6AHTWTR3PM3EY37CYNT/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q3IGBH6AHTWTR3PM3EY37CYNT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT/action/storage_attestation","attest_author":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT/action/author_attestation","sign_citation":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT/action/citation_signature","submit_replication":"https://pith.science/pith/7Q3IGBH6AHTWTR3PM3EY37CYNT/action/replication_record"}},"created_at":"2026-07-05T11:12:19.073763+00:00","updated_at":"2026-07-05T11:12:19.073763+00:00"}