{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4J73IFXG6ZOGJO7NJ2BJEORKDZ","short_pith_number":"pith:4J73IFXG","schema_version":"1.0","canonical_sha256":"e27fb416e6f65c64bbed4e82923a2a1e51a65ecc10302a996c6efbd0584f6318","source":{"kind":"arxiv","id":"2503.00711","version":1},"attestation_state":"computed","paper":{"title":"OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cheng Ding, Jia Mao, Qianhao Yu, Wenfeng Duan, Zhijiang Wan","submitted_at":"2025-03-02T03:26:14Z","abstract_excerpt":"This study introduces OpenECG, a large-scale benchmark of 1.2 million 12-lead ECG recordings from nine centers, to evaluate ECG foundation models (ECG-FMs) trained on public datasets. We investigate three self-supervised learning methods (SimCLR, BYOL, MAE) with ResNet-50 and Vision Transformer architectures, assessing model generalization through leave-one-dataset-out experiments and data scaling analysis. Results show that pre-training on diverse datasets significantly improves generalization, with BYOL and MAE outperforming SimCLR, highlighting the efficacy of feature-consistency and genera"},"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":"2503.00711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-02T03:26:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7cdb821c2c122275364612c2e1c1e17c23924a2c61f8b7332bceea4df7e74330","abstract_canon_sha256":"7f2d4d03ce2ef83a7383b358f4c76eb3c75e88895c96e270afe132c8d9a6befb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:28.008162Z","signature_b64":"AxBBL5tI9zJxSNPe0qg3xWokIpJzQOP5hpE3bmGLtcct7M2a6lgmr/dwTo81KGdqcZwyzyjxqO8LH/klue1rCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e27fb416e6f65c64bbed4e82923a2a1e51a65ecc10302a996c6efbd0584f6318","last_reissued_at":"2026-07-05T10:22:28.006534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:28.006534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cheng Ding, Jia Mao, Qianhao Yu, Wenfeng Duan, Zhijiang Wan","submitted_at":"2025-03-02T03:26:14Z","abstract_excerpt":"This study introduces OpenECG, a large-scale benchmark of 1.2 million 12-lead ECG recordings from nine centers, to evaluate ECG foundation models (ECG-FMs) trained on public datasets. We investigate three self-supervised learning methods (SimCLR, BYOL, MAE) with ResNet-50 and Vision Transformer architectures, assessing model generalization through leave-one-dataset-out experiments and data scaling analysis. Results show that pre-training on diverse datasets significantly improves generalization, with BYOL and MAE outperforming SimCLR, highlighting the efficacy of feature-consistency and genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00711","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/2503.00711/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":"2503.00711","created_at":"2026-07-05T10:22:28.007640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00711v1","created_at":"2026-07-05T10:22:28.007640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00711","created_at":"2026-07-05T10:22:28.007640+00:00"},{"alias_kind":"pith_short_12","alias_value":"4J73IFXG6ZOG","created_at":"2026-07-05T10:22:28.007640+00:00"},{"alias_kind":"pith_short_16","alias_value":"4J73IFXG6ZOGJO7N","created_at":"2026-07-05T10:22:28.007640+00:00"},{"alias_kind":"pith_short_8","alias_value":"4J73IFXG","created_at":"2026-07-05T10:22:28.007640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16975","citing_title":"Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12241","citing_title":"Pretraining Strategies and Scaling for ECG Foundation Models: A Systematic Study","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02500","citing_title":"Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ","json":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ.json","graph_json":"https://pith.science/api/pith-number/4J73IFXG6ZOGJO7NJ2BJEORKDZ/graph.json","events_json":"https://pith.science/api/pith-number/4J73IFXG6ZOGJO7NJ2BJEORKDZ/events.json","paper":"https://pith.science/paper/4J73IFXG"},"agent_actions":{"view_html":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ","download_json":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ.json","view_paper":"https://pith.science/paper/4J73IFXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00711&json=true","fetch_graph":"https://pith.science/api/pith-number/4J73IFXG6ZOGJO7NJ2BJEORKDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4J73IFXG6ZOGJO7NJ2BJEORKDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ/action/storage_attestation","attest_author":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ/action/author_attestation","sign_citation":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ/action/citation_signature","submit_replication":"https://pith.science/pith/4J73IFXG6ZOGJO7NJ2BJEORKDZ/action/replication_record"}},"created_at":"2026-07-05T10:22:28.007640+00:00","updated_at":"2026-07-05T10:22:28.007640+00:00"}