{"id":"W4365601120","doi":"10.48550/arxiv.2304.06427","title":"In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detection","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Representation (politics); Machine learning; Set (abstract data type); Training set; Pattern recognition (psychology); Feature learning; Data mining","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005661314,0.0009976237,0.001008824,0.001529269,0.0004699395,0.001065255,0.001625025,0.001232749,0.0009875622],"category_scores_gemma":[0.01650503,0.0002846715,0.00079865,0.0009808855,0.001161269,0.001971378,0.001679073,0.001649584,0.0007786902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005915586,"about_ca_system_score_gemma":0.0008054356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008452543,"about_ca_topic_score_gemma":0.00154411,"domain_scores_codex":[0.9964474,0.001721637,0.0001817707,0.0008119246,0.0006857777,0.0001516028],"domain_scores_gemma":[0.9891005,0.006012471,0.0009042079,0.002458673,0.001239261,0.0002848246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007564257,0.001036656,0.03012754,0.0004668784,0.0003938498,0.0001859023,0.0003534491,0.1598576,0.01091279,0.006799266,0.01035822,0.7787515],"study_design_scores_gemma":[0.00002978863,0.000229014,0.003689996,0.00002994728,0.00002846766,0.000226026,0.00006591146,0.9827713,0.005899116,0.00543106,0.0015732,0.00002610325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1434672,0.001976985,0.8474005,0.0007218444,0.0001493767,0.0001792876,0.0005247845,0.002389433,0.00319056],"genre_scores_gemma":[0.8253494,0.0005863018,0.1685997,0.0005204576,0.0002709276,0.0001522771,0.001919527,0.0002456398,0.002355698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005661314,"threshold_uncertainty_score":0.02994025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08393364166807105,"score_gpt":0.2455842208353014,"score_spread":0.1616505791672304,"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."}}