{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0143295,0.0001771527,0.0004300814,0.0001400097,0.000477226,0.00003528899,0.0008572638,0.0002944011,0.001910253],"category_scores_gemma":[0.4438069,0.0001459615,0.0001215691,0.00168931,0.001117336,0.000198821,0.00007866447,0.0007767747,0.00002238963],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007050073,"about_ca_system_score_gemma":0.02488602,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02656566,"about_ca_topic_score_gemma":0.001299149,"domain_scores_codex":[0.9889504,0.003885088,0.001137065,0.0006002772,0.005098983,0.000328208],"domain_scores_gemma":[0.9848543,0.009583864,0.001280536,0.0007217158,0.002400217,0.00115933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001287278,0.006066697,0.05428139,0.0001756528,0.00002534174,7.685207e-8,0.795644,0.000004304909,0.00003517662,0.02369458,0.00130269,0.1186414],"study_design_scores_gemma":[0.000497054,0.0007414197,0.1610069,0.0002195742,0.00005518146,4.788232e-7,0.8326836,0.0001754215,0.00002773969,0.001980624,0.002425569,0.000186419],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8389314,0.0004936103,0.00008934559,0.1538383,0.002891839,0.00214681,0.000002944092,0.000050358,0.001555384],"genre_scores_gemma":[0.9939795,0.0002640358,0.0008134409,0.001653139,0.002569636,0.0006540567,0.00001309961,0.0000181561,0.00003498135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4294774,"threshold_uncertainty_score":0.9990022,"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."}}