{"id":"W3027127350","doi":"10.36834/cmej.70331","title":"A plea for program evaluation in a pandemic","year":2020,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Plea; Pandemic; Computer science; Coronavirus disease 2019 (COVID-19); Data science; Medicine; Political science; Law; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.009215527,0.00007283805,0.0001388373,0.0003451026,0.0001466152,0.0002235997,0.0004276983,0.0001023216,0.04797296],"category_scores_gemma":[0.07388241,0.00005713148,0.0000620871,0.0006809024,0.00003972339,0.0002651969,0.000008441825,0.0003477753,0.000161342],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003970208,"about_ca_system_score_gemma":0.0929211,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005200795,"about_ca_topic_score_gemma":0.03595916,"domain_scores_codex":[0.9963831,0.0002648925,0.0006311085,0.0002059796,0.002259161,0.0002558154],"domain_scores_gemma":[0.994037,0.0002290253,0.0001616006,0.0001188291,0.0009997413,0.004453791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008317287,0.00002787737,0.0100112,0.000002239444,0.000002858988,9.043889e-7,0.001316567,0.00006348262,0.000001606502,0.000269255,0.09524372,0.893052],"study_design_scores_gemma":[0.00081968,0.0001199864,0.01930614,0.00003044723,0.000008008869,0.00004305045,0.002745526,0.1479151,0.000001360583,0.004733375,0.824191,0.0000863156],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2670227,0.0007288897,0.002327261,0.7121484,0.003459001,0.002963092,0.00001137918,0.00003358733,0.01130564],"genre_scores_gemma":[0.9366699,0.00004008372,0.001879911,0.05930551,0.00140742,0.0004159565,0.00001938897,0.00000852167,0.0002532871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8929657,"threshold_uncertainty_score":0.9816321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3190357027594689,"score_gpt":0.5713732575257328,"score_spread":0.2523375547662639,"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."}}