{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.04936818,0.0002738693,0.0004115543,0.000249358,0.0006379839,0.001730066,0.0002668687,0.00009758817,0.00150051],"category_scores_gemma":[0.005646829,0.0002162306,0.00009401239,0.001286636,0.00007764383,0.001179296,0.00008169268,0.0002940441,0.00005418792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009613822,"about_ca_system_score_gemma":0.001529508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003022467,"about_ca_topic_score_gemma":0.00004157557,"domain_scores_codex":[0.9873039,0.00605525,0.001119897,0.0008080787,0.00436195,0.0003509213],"domain_scores_gemma":[0.9949549,0.001682679,0.0006327132,0.0004229234,0.001953459,0.0003533471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003676923,0.0002885021,0.04928688,0.00001049763,0.00003767153,0.00004570014,0.007974488,0.01044823,0.0001257688,0.00002764078,0.0003660563,0.9313518],"study_design_scores_gemma":[0.00263259,0.0007811738,0.06424096,0.00003851803,0.000305328,0.00007323865,0.0576898,0.8723553,0.0000781127,0.0005778493,0.0009797023,0.0002474248],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.959688,0.0008400607,0.03008668,0.003237822,0.0004690084,0.003478701,0.000004500722,0.0001843838,0.002010813],"genre_scores_gemma":[0.9321557,0.000001584999,0.06631465,0.0009062781,0.0001296803,0.0004113376,0.000055681,0.00001782975,0.000007227832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9311044,"threshold_uncertainty_score":0.9994122,"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."}}