{"id":"W7117151570","doi":"10.48550/arxiv.2512.18031","title":"A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Atrial fibrillation; Intensive care unit; Deep learning; Intensive care; Inference; Cardiac arrhythmia; Transfer of learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001515334,0.0004296917,0.0009708276,0.0005831869,0.0002384486,0.00003258544,0.0002244691,0.0005630725,0.0000208747],"category_scores_gemma":[0.0006067856,0.0005112658,0.0007212559,0.0007604707,0.0001501593,0.0001359258,0.0004182014,0.0004677351,0.00000214622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002828104,"about_ca_system_score_gemma":0.0002069702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003136867,"about_ca_topic_score_gemma":0.000232218,"domain_scores_codex":[0.9977034,0.0001879765,0.0004639653,0.001172816,0.0001324617,0.0003394245],"domain_scores_gemma":[0.9952523,0.0004439733,0.0005888088,0.0007643952,0.002767615,0.000182985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007308224,0.0000611869,0.8585114,0.001660659,0.007328391,0.00002752488,0.001446778,0.06442275,0.0003188238,0.00007346047,0.0002731803,0.05856762],"study_design_scores_gemma":[0.04217391,0.006578434,0.117359,0.00785563,0.08476662,0.000003905375,0.0488626,0.654763,0.01310559,0.004587805,0.01629278,0.003650698],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9675013,0.000819411,0.02088013,0.00001506327,0.001015808,0.0009953337,0.008680778,0.00002229985,0.00006988615],"genre_scores_gemma":[0.970163,0.001983284,0.0001122377,0.00001866498,0.0007246936,8.792271e-7,0.02686287,0.00001759113,0.0001167387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7411525,"threshold_uncertainty_score":0.9997339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04441572526403081,"score_gpt":0.2210310616958162,"score_spread":0.1766153364317853,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}