{"paper":{"title":"Label-Conditioned Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Curriculum-Gated Contrastive Alignment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Structured clinical semantic supervision aligns adult ECG features with pediatric diagnostic targets to improve low-resource transfer.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengyu Liu, Heyang Xu, Hongxiang Gao, Jianqing Li, Xinran Liu, Yuwen Li, Zongmin Wang","submitted_at":"2026-05-01T13:28:56Z","abstract_excerpt":"Automated pediatric electrocardiogram (ECG) interpretation remains challenging because developmental differences in heart rate, intervals, and waveforms limit the transferability of models trained mainly on adult data, while expert-labeled pediatric ECG cohorts are scarce. We propose PEACE (Pediatric-Adult ECG Alignment via Cross-modal Enhancement), an adult-to-pediatric ECG transfer framework pretrained on MIMIC-IV ECGs and adapted to pediatric targets. PEACE integrates label-specific bidirectional contrastive learning (LSBC) to align ECG representations with diagnostic semantics and curricul"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"structured clinical semantic supervision can improve low-resource adult-to-pediatric ECG transfer","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Gemini-generated label-conditioned semantic descriptors accurately capture clinically relevant ECG semantics and provide effective auxiliary supervision without introducing bias or noise, despite the absence of paired clinical reports.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PEACE framework aligns adult and pediatric ECGs via tri-axial semantic decomposition and LLM-generated auxiliary supervision, achieving 59.39% zero-shot to 90.89% full fine-tuning AUC on ZZU-pECG.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Structured clinical semantic supervision aligns adult ECG features with pediatric diagnostic targets to improve low-resource transfer.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b4973c43a46b671baf1c6497061ea8adc5aa27bd9a593beb4e354b706c9d3e62"},"source":{"id":"2605.00647","kind":"arxiv","version":2},"verdict":{"id":"9dd51c5d-2240-46f8-8285-689cf433ff53","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T19:57:36.575895Z","strongest_claim":"structured clinical semantic supervision can improve low-resource adult-to-pediatric ECG transfer","one_line_summary":"PEACE framework aligns adult and pediatric ECGs via tri-axial semantic decomposition and LLM-generated auxiliary supervision, achieving 59.39% zero-shot to 90.89% full fine-tuning AUC on ZZU-pECG.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Gemini-generated label-conditioned semantic descriptors accurately capture clinically relevant ECG semantics and provide effective auxiliary supervision without introducing bias or noise, despite the absence of paired clinical reports.","pith_extraction_headline":"Structured clinical semantic supervision aligns adult ECG features with pediatric diagnostic targets to improve low-resource transfer."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00647/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T19:38:11.561506Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:57:01.885357Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ca8f580a7c70b9a6e75ca9cc6dc152084cb5e829f56c33dc73cee7e77768431c"},"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"}