{"id":"W3173744756","doi":"10.1186/s12909-021-02797-3","title":"Psychometric validation of the Laval developmental benchmarks scale for family medicine","year":2021,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Medical Council of Canada","keywords":"Rasch model; Convergent validity; Rating scale; Scale (ratio); Psychology; Summative assessment; Reliability (semiconductor); Clinical psychology; Psychometrics; Inter-rater reliability; Formative assessment; Developmental psychology; Internal consistency; Mathematics education","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.01002519,0.0002229414,0.0002985721,0.00145397,0.0004827425,0.0005788548,0.0007312448,0.0003498753,0.001353842],"category_scores_gemma":[0.03640066,0.000175199,0.0005257063,0.0007168767,0.0005974287,0.0006724396,0.001431658,0.0007231981,0.0002670491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234805,"about_ca_system_score_gemma":0.002379415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005169648,"about_ca_topic_score_gemma":0.009231424,"domain_scores_codex":[0.9948486,0.002037999,0.0005267501,0.000280342,0.002128144,0.0001780899],"domain_scores_gemma":[0.9824002,0.007024024,0.003532657,0.0007997042,0.005112543,0.001130908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001454376,0.000267968,0.9095954,0.00008110733,0.00009014784,0.00005513797,0.001221619,0.0005075944,0.0004088123,0.0004680581,0.003535145,0.08362366],"study_design_scores_gemma":[0.00003801328,0.0003205608,0.9934747,0.0001289944,0.00001925826,0.0001815807,0.0005643366,0.001352663,0.0002950639,0.0002393407,0.003370698,0.00001489795],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.984467,0.0009025609,0.004031093,0.0009493143,0.00007785041,0.0008595886,0.00106513,0.00007150873,0.00757587],"genre_scores_gemma":[0.9874257,0.0002404391,0.009907411,0.0001418347,0.0000217263,0.0007315553,0.0009037329,0.00001322352,0.0006143581],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01002519,"threshold_uncertainty_score":0.05301887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03583883828791896,"score_gpt":0.3708217044386655,"score_spread":0.3349828661507466,"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."}}