{"id":"W2896892568","doi":"10.1080/0142159x.2018.1500016","title":"2018 Consensus framework for good assessment","year":2018,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Innovations in Medical Education","field":"Medicine","cited_by":315,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Set (abstract data type); Task (project management); Task group; Medical education; Diversity (politics); Field (mathematics); Representation (politics); Management science; Computer science; Medicine; Psychology; Political science; Engineering management; Management; Engineering; Law; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2935998,0.002434698,0.003563877,0.01476258,0.01091646,0.02276626,0.01122279,0.01766164,0.01518635],"category_scores_gemma":[0.3015861,0.001926741,0.005061278,0.008729368,0.03587135,0.01496622,0.01764606,0.01324351,0.00571878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0474201,"about_ca_system_score_gemma":0.1155744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02530452,"about_ca_topic_score_gemma":0.0154057,"domain_scores_codex":[0.5767034,0.2974357,0.04693025,0.01899229,0.0518043,0.008134027],"domain_scores_gemma":[0.6486297,0.1768064,0.01413942,0.01861529,0.1309562,0.01085286],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002962898,0.00002831612,0.0004061532,0.001176844,0.00006254802,0.0001294942,0.003886538,0.001375844,0.0000594522,0.9428104,0.02038718,0.02964766],"study_design_scores_gemma":[0.00006350298,0.00004919566,0.0004855266,0.004683716,0.00005242577,0.0001848018,0.002864539,0.002517599,0.0001611137,0.8313293,0.157527,0.00008132726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002561,0.01159148,0.5350151,0.1817203,0.004213094,0.006165342,0.001270406,0.0005466464,0.2569167],"genre_scores_gemma":[0.2274725,0.006177105,0.7070925,0.02075153,0.001596703,0.01575364,0.001794374,0.0003315213,0.01903002],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7064002,"threshold_uncertainty_score":0.8711172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04215607722440534,"score_gpt":0.4338291115566985,"score_spread":0.3916730343322932,"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."}}