{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001355258,0.0001282831,0.0002436522,0.0000840377,0.0001276482,0.00001214362,0.0001398326,0.0003980465,0.01193946],"category_scores_gemma":[0.008321871,0.0001011847,0.0000712152,0.0003001677,0.0005576583,0.00001820435,0.00003707441,0.0006377831,0.0002774818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001761319,"about_ca_system_score_gemma":0.0005665592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001153045,"about_ca_topic_score_gemma":0.000002325805,"domain_scores_codex":[0.998266,0.00005129268,0.0003791578,0.0002821735,0.0006913377,0.0003300184],"domain_scores_gemma":[0.9988827,0.0001048092,0.0000804162,0.0004082405,0.0002930078,0.0002308261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008730537,0.0009912992,0.03420376,0.0001058511,0.000135721,0.00001357338,0.0004978707,2.635053e-8,0.0000462329,0.08827418,0.7541493,0.1214949],"study_design_scores_gemma":[0.002593181,0.001040413,0.01218091,0.0004756784,0.0001572532,0.0001100772,0.0006781731,0.01349058,0.0001282158,0.02425766,0.9446113,0.0002766008],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5423002,0.0001065739,0.2429688,0.133436,0.005508377,0.001235329,0.000003482889,0.0003077388,0.07413353],"genre_scores_gemma":[0.7774612,0.000008085761,0.1882596,0.01262048,0.008305704,0.0002351359,0.00007636028,0.0000557846,0.01297759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2351611,"threshold_uncertainty_score":0.9962658,"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."}}