{"id":"W2885480655","doi":"10.1111/medu.13645","title":"Assessment, feedback and the alchemy of learning","year":2018,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":416,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Western University","funders":"","keywords":"Formative assessment; Summative assessment; Competence (human resources); CLARITY; Assessment for learning; Judgement; Psychology; Peer feedback; Pedagogy; Medical education; Social psychology; Medicine; Political science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001473357,0.00003749304,0.0000799803,0.00002239707,0.0002969926,0.00003042952,0.000147506,0.00005287528,0.00134963],"category_scores_gemma":[0.001070233,0.00002522231,0.00002099733,0.0001574883,0.001091849,0.00006762557,0.0000345936,0.0001123649,0.00001689747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002382253,"about_ca_system_score_gemma":0.0007435432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006289145,"about_ca_topic_score_gemma":0.0001685428,"domain_scores_codex":[0.9990102,0.0001939758,0.0001164386,0.00008603642,0.0004868904,0.0001064396],"domain_scores_gemma":[0.9995126,0.0002008571,0.00007165873,0.0000596274,0.00009791645,0.00005736945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003546731,0.0003212567,0.3868549,0.00002110278,0.0000457952,1.5402e-7,0.06734312,7.316738e-8,0.00008167806,0.3550224,0.03715706,0.1531171],"study_design_scores_gemma":[0.001633114,0.00009435846,0.4128882,0.00009226897,0.00005382319,0.000001000764,0.07357973,0.0003531657,0.00004968468,0.00520319,0.5058989,0.0001525972],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5962722,0.0001732948,0.0003243654,0.02839682,0.0009443159,0.0002123156,1.162381e-7,0.0000266014,0.37365],"genre_scores_gemma":[0.9947814,0.000183422,0.0002627277,0.0006316566,0.0007019123,0.00001175621,0.000002016797,0.000002855348,0.003422265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4687418,"threshold_uncertainty_score":0.9995633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01469089774875304,"score_gpt":0.3976035401559191,"score_spread":0.3829126424071661,"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."}}