{"id":"W4411445091","doi":"10.7202/1118374ar","title":"Narrative of a Practice for the Adaptation and Use of a Training tool for Evaluative Judgment Based on Concordance","year":2023,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Université de Montréal","funders":"","keywords":"Formative assessment; Concordance; Adaptation (eye); Interpretation (philosophy); Narrative; Context (archaeology); Psychology; Test (biology); Pedagogy; Applied psychology; Mathematics education; Cognitive psychology; Computer science; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1245215,0.001092679,0.0007317774,0.002962694,0.007742169,0.005486022,0.004021332,0.005320249,0.003520278],"category_scores_gemma":[0.1443973,0.0008668457,0.001373022,0.001250195,0.01600775,0.008232133,0.009994283,0.01136639,0.00225094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004384717,"about_ca_system_score_gemma":0.01550129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002642093,"about_ca_topic_score_gemma":0.004893092,"domain_scores_codex":[0.8796044,0.09998995,0.005129336,0.004233188,0.009656262,0.001386914],"domain_scores_gemma":[0.8605705,0.07440847,0.007127632,0.02673914,0.02482799,0.006326215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002674925,0.001493343,0.006008016,0.002347521,0.00007978517,0.003209435,0.2386081,0.001773984,0.008029724,0.2427902,0.08117778,0.4142147],"study_design_scores_gemma":[0.000179798,0.0009075004,0.00419912,0.008443868,0.00008219263,0.008259857,0.06052566,0.006313056,0.008458863,0.09405159,0.8081518,0.0004267367],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04123849,0.002639875,0.7280198,0.1442859,0.003909647,0.00526094,0.0001279016,0.001777776,0.07273959],"genre_scores_gemma":[0.1940277,0.001050075,0.779697,0.008686149,0.0003004009,0.003578505,0.00006423,0.0003205783,0.01227529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1245215,"threshold_uncertainty_score":0.6585406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2418321036963189,"score_gpt":0.4766062542430951,"score_spread":0.2347741505467762,"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."}}