{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GIFZ2KDSX5GE6MB3IVBJ7N3KQ5","short_pith_number":"pith:GIFZ2KDS","schema_version":"1.0","canonical_sha256":"320b9d2872bf4c4f303b45429fb76a874c8864c77187b91fbecedeb619aa20f4","source":{"kind":"arxiv","id":"2605.17276","version":1},"attestation_state":"computed","paper":{"title":"How Do Electrocardiogram Models Scale?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ant\\^onio H. Ribeiro, Fabio Bonassi, Jiawei Li, Johan Sundstr\\\"om, Ming Jin, Stefan Gustafsson, Thomas B. Sch\\\"on","submitted_at":"2026-05-17T05:53:35Z","abstract_excerpt":"While scaling laws have established a fundamental framework for foundation models in natural language processing, their applicability to electrocardiogram (ECG) models remains poorly characterized. Indeed, recent studies do not always yield consistent downstream gains as one increases the model size or pre-training dataset size of ECG models, leaving the exact roles of architectural inductive biases, pre-training paradigms, and expected improvements with size largely unanswered. In this work, we systematically investigate neural and loss-to-loss scaling laws within the ECG domain. By pre-train"},"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":"2605.17276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T05:53:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4aab53c1a31b3388bc57ef9e078669dbef64b3417f46af917b767f957385a59e","abstract_canon_sha256":"850356e11ed7e9380641ff4793c2a737ab9c3e244769766cd36d3bc49c6780ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:49.310576Z","signature_b64":"1ONGcUpbcL8rijcnrzhQTBgDlOu7an7VmX+zKzFnXuFwBRoZUQLRcraoLIg7plBdP0TvsO23aR4gNILk0VbKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320b9d2872bf4c4f303b45429fb76a874c8864c77187b91fbecedeb619aa20f4","last_reissued_at":"2026-05-20T00:03:49.309749Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:49.309749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Do Electrocardiogram Models Scale?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ant\\^onio H. Ribeiro, Fabio Bonassi, Jiawei Li, Johan Sundstr\\\"om, Ming Jin, Stefan Gustafsson, Thomas B. Sch\\\"on","submitted_at":"2026-05-17T05:53:35Z","abstract_excerpt":"While scaling laws have established a fundamental framework for foundation models in natural language processing, their applicability to electrocardiogram (ECG) models remains poorly characterized. Indeed, recent studies do not always yield consistent downstream gains as one increases the model size or pre-training dataset size of ECG models, leaving the exact roles of architectural inductive biases, pre-training paradigms, and expected improvements with size largely unanswered. In this work, we systematically investigate neural and loss-to-loss scaling laws within the ECG domain. By pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17276","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/2605.17276/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.831434Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.775091Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7fe51379bf255288dd30e0c1bfbb817ce7493faac57f652ce478d53e25b7b60e"},"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":"2605.17276","created_at":"2026-05-20T00:03:49.309886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17276v1","created_at":"2026-05-20T00:03:49.309886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17276","created_at":"2026-05-20T00:03:49.309886+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIFZ2KDSX5GE","created_at":"2026-05-20T00:03:49.309886+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIFZ2KDSX5GE6MB3","created_at":"2026-05-20T00:03:49.309886+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIFZ2KDS","created_at":"2026-05-20T00:03:49.309886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5","json":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5.json","graph_json":"https://pith.science/api/pith-number/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/graph.json","events_json":"https://pith.science/api/pith-number/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/events.json","paper":"https://pith.science/paper/GIFZ2KDS"},"agent_actions":{"view_html":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5","download_json":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5.json","view_paper":"https://pith.science/paper/GIFZ2KDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17276&json=true","fetch_graph":"https://pith.science/api/pith-number/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/action/storage_attestation","attest_author":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/action/author_attestation","sign_citation":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/action/citation_signature","submit_replication":"https://pith.science/pith/GIFZ2KDSX5GE6MB3IVBJ7N3KQ5/action/replication_record"}},"created_at":"2026-05-20T00:03:49.309886+00:00","updated_at":"2026-05-20T00:03:49.309886+00:00"}