{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S2RAEY4J2LAJE323HZJGJUWBAF","short_pith_number":"pith:S2RAEY4J","schema_version":"1.0","canonical_sha256":"96a2026389d2c0926f5b3e5264d2c1015271aae98f5c48fa0a1f1dc589e066a8","source":{"kind":"arxiv","id":"2509.10151","version":1},"attestation_state":"computed","paper":{"title":"BenchECG and xECG: a benchmark and baseline for ECG foundation models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Angus Nicolson, Axel Bauer, Clemens Dlaska, Riccardo Lunelli, Samuel Martin Pr\\\"oll, Sebastian Johannes Reinstadler","submitted_at":"2025-09-12T11:27:17Z","abstract_excerpt":"Electrocardiograms (ECGs) are inexpensive, widely used, and well-suited to deep learning. Recently, interest has grown in developing foundation models for ECGs - models that generalise across diverse downstream tasks. However, consistent evaluation has been lacking: prior work often uses narrow task selections and inconsistent datasets, hindering fair comparison. Here, we introduce BenchECG, a standardised benchmark comprising a comprehensive suite of publicly available ECG datasets and versatile tasks. We also propose xECG, an xLSTM-based recurrent model trained with SimDINOv2 self-supervised"},"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":"2509.10151","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-12T11:27:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ab5e06293270b26d9e93e860857e71ab1ba04b40fe720fc2230c64d0b6dc4707","abstract_canon_sha256":"78ccab82a6a28357d08ae17a98b1815e6b5066d7a8fae66e9701abec39f5c850"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:04.013351Z","signature_b64":"Z+05eX1tCN1N/wWm6WAewz9H365xIaIAytXOhFnVKg793FgM/tPLhkKbuPNw03jlx9nzVlv1kvQObn76c/6lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96a2026389d2c0926f5b3e5264d2c1015271aae98f5c48fa0a1f1dc589e066a8","last_reissued_at":"2026-07-05T12:11:04.012744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:04.012744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BenchECG and xECG: a benchmark and baseline for ECG foundation models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Angus Nicolson, Axel Bauer, Clemens Dlaska, Riccardo Lunelli, Samuel Martin Pr\\\"oll, Sebastian Johannes Reinstadler","submitted_at":"2025-09-12T11:27:17Z","abstract_excerpt":"Electrocardiograms (ECGs) are inexpensive, widely used, and well-suited to deep learning. Recently, interest has grown in developing foundation models for ECGs - models that generalise across diverse downstream tasks. However, consistent evaluation has been lacking: prior work often uses narrow task selections and inconsistent datasets, hindering fair comparison. Here, we introduce BenchECG, a standardised benchmark comprising a comprehensive suite of publicly available ECG datasets and versatile tasks. We also propose xECG, an xLSTM-based recurrent model trained with SimDINOv2 self-supervised"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10151","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/2509.10151/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":"2509.10151","created_at":"2026-07-05T12:11:04.012826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10151v1","created_at":"2026-07-05T12:11:04.012826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10151","created_at":"2026-07-05T12:11:04.012826+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2RAEY4J2LAJ","created_at":"2026-07-05T12:11:04.012826+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2RAEY4J2LAJE323","created_at":"2026-07-05T12:11:04.012826+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2RAEY4J","created_at":"2026-07-05T12:11:04.012826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02605","citing_title":"Cross-Modal Contrastive Learning of ECG and Angiography Representations for Severe Stenosis Classification","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16441","citing_title":"DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17276","citing_title":"How Do Electrocardiogram Models Scale?","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12241","citing_title":"Pretraining Strategies and Scaling for ECG Foundation Models: A Systematic Study","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF","json":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF.json","graph_json":"https://pith.science/api/pith-number/S2RAEY4J2LAJE323HZJGJUWBAF/graph.json","events_json":"https://pith.science/api/pith-number/S2RAEY4J2LAJE323HZJGJUWBAF/events.json","paper":"https://pith.science/paper/S2RAEY4J"},"agent_actions":{"view_html":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF","download_json":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF.json","view_paper":"https://pith.science/paper/S2RAEY4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10151&json=true","fetch_graph":"https://pith.science/api/pith-number/S2RAEY4J2LAJE323HZJGJUWBAF/graph.json","fetch_events":"https://pith.science/api/pith-number/S2RAEY4J2LAJE323HZJGJUWBAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF/action/storage_attestation","attest_author":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF/action/author_attestation","sign_citation":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF/action/citation_signature","submit_replication":"https://pith.science/pith/S2RAEY4J2LAJE323HZJGJUWBAF/action/replication_record"}},"created_at":"2026-07-05T12:11:04.012826+00:00","updated_at":"2026-07-05T12:11:04.012826+00:00"}