{"id":"W2965938650","doi":"10.1097/acm.0000000000002908","title":"What’s Next? Developing Systems of Assessment for Educational Settings","year":2019,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Competence (human resources); Educational assessment; Medical education; Systems thinking; Needs assessment; Psychology; Engineering ethics; Computer science; Mathematics education; Medicine; Political science; Engineering; Artificial intelligence; Social psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0469999,0.001953884,0.001599288,0.00525453,0.00627696,0.02406534,0.005934469,0.005759998,0.009546829],"category_scores_gemma":[0.08326314,0.001264794,0.002252734,0.004410999,0.01111363,0.04415423,0.01281543,0.008396819,0.00439615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01370411,"about_ca_system_score_gemma":0.02764177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01366319,"about_ca_topic_score_gemma":0.0167728,"domain_scores_codex":[0.9530811,0.0295964,0.003247313,0.00436567,0.00771384,0.001995767],"domain_scores_gemma":[0.9420878,0.0193902,0.004267988,0.009925786,0.0193284,0.004999927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005667095,0.0002384127,0.0121474,0.001519001,0.0001482913,0.0002101017,0.01472072,0.004636423,0.0007844475,0.409173,0.03947996,0.5168855],"study_design_scores_gemma":[0.0000487314,0.0002398949,0.004399372,0.00574216,0.0001072355,0.0004795574,0.01255924,0.01263795,0.001490765,0.5460418,0.4159523,0.0003010726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01123425,0.02149264,0.7341285,0.1518015,0.004065358,0.001495629,0.0004057071,0.003061799,0.07231469],"genre_scores_gemma":[0.08405571,0.006179656,0.8980709,0.004643854,0.0006182533,0.001140421,0.0003389319,0.0004121097,0.004540133],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0469999,"threshold_uncertainty_score":0.2485622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0441342751167448,"score_gpt":0.4198399100694857,"score_spread":0.3757056349527409,"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."}}