{"id":"W3003697964","doi":"10.1016/j.evalprogplan.2020.101789","title":"Assessing competency-based evaluation course impacts: A mixed methods case study","year":2020,"lang":"en","type":"article","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; University of Alberta","funders":"","keywords":"Context (archaeology); Presentation (obstetrics); Process (computing); Knowledge management; Focus group; Medical education; Computer science; Engineering ethics; Engineering; Sociology; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03487958,0.0008888642,0.0008751841,0.002424919,0.003719789,0.002794428,0.00264388,0.002558116,0.003010926],"category_scores_gemma":[0.04472117,0.0005858405,0.0008842217,0.001416938,0.001191351,0.002022307,0.003075377,0.001652516,0.0004338595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005909864,"about_ca_system_score_gemma":0.007221439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005919447,"about_ca_topic_score_gemma":0.01324321,"domain_scores_codex":[0.9714808,0.02131552,0.001020889,0.001027119,0.003495293,0.00166042],"domain_scores_gemma":[0.9344246,0.04927589,0.002762205,0.002826578,0.007666267,0.003044563],"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":[0.01153789,0.1565799,0.1729682,0.002798072,0.0007678416,0.008347941,0.06861199,0.02321504,0.01522684,0.01207931,0.003956957,0.5239101],"study_design_scores_gemma":[0.008252976,0.1932747,0.2647105,0.004738715,0.0019061,0.009515337,0.2228861,0.1508541,0.07892835,0.02014081,0.04364264,0.001149705],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813982,0.0001978303,0.01064015,0.0004136338,0.00002704897,0.003114981,0.0001549047,0.00002607772,0.004027196],"genre_scores_gemma":[0.9584928,0.0002890516,0.03626323,0.0002474668,0.0000227451,0.002722434,0.00008426365,0.00001699158,0.001860993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03487958,"threshold_uncertainty_score":0.1844631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4928499038396967,"score_gpt":0.6787705841841661,"score_spread":0.1859206803444695,"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."}}