{"id":"W3032548481","doi":"10.1007/s40037-020-00589-x","title":"Evaluating the reliability of gestalt quality ratings of medical education podcasts: A METRIQ study","year":2020,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Saskatchewan","funders":"","keywords":"Likert scale; Quality (philosophy); Medical education; Reliability (semiconductor); Gestalt psychology; Psychology; Medicine; Applied psychology","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06168626,0.0003059142,0.0006591216,0.002134239,0.0007319173,0.001236294,0.0007821129,0.0004851667,0.001631025],"category_scores_gemma":[0.1480192,0.0003813512,0.0007319242,0.001405746,0.001365383,0.001290987,0.002751842,0.0007100404,0.0003786861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007191751,"about_ca_system_score_gemma":0.001100267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001578061,"about_ca_topic_score_gemma":0.001927213,"domain_scores_codex":[0.9540471,0.02877514,0.004802955,0.002370738,0.008959476,0.001044509],"domain_scores_gemma":[0.8424482,0.08951666,0.02265641,0.009954548,0.03261957,0.002804623],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005059754,0.0002411277,0.9492095,0.0002365609,0.0002731683,0.00005414686,0.01679914,0.000262621,0.0008966819,0.0003914734,0.0008055931,0.03032409],"study_design_scores_gemma":[0.00006068644,0.0008243928,0.9804834,0.000172667,0.0000987156,0.0001986828,0.01066402,0.003330059,0.001068797,0.0002967596,0.002758241,0.00004362376],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912298,0.0001831297,0.004672974,0.0001749532,0.00005432671,0.0004241402,0.0002664945,0.00002665203,0.002967602],"genre_scores_gemma":[0.9967013,0.00006456782,0.002403491,0.00003425353,0.00002380104,0.0003876386,0.0001530094,0.00001232825,0.0002196402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9383137,"threshold_uncertainty_score":0.326232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2466045087206723,"score_gpt":0.5819969445789384,"score_spread":0.3353924358582661,"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."}}