{"id":"W2946644535","doi":"10.5539/jel.v8n3p122","title":"Evaluation of Learning Outcomes Through Multiple Choice Pre- and Post-Training Assessments","year":2019,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Inclusion (mineral); Control (management); Medical education; Construct (python library); Program evaluation; Applied psychology; Mathematics education; Social psychology; Computer science; Artificial intelligence; Medicine; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018548,0.0009238308,0.001264419,0.002330295,0.0007428288,0.0009688137,0.0008883367,0.0005795035,0.005409901],"category_scores_gemma":[0.04124429,0.000282504,0.001218343,0.001210447,0.000780749,0.001275345,0.001301966,0.001214519,0.001859154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000707438,"about_ca_system_score_gemma":0.001210767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007693879,"about_ca_topic_score_gemma":0.002015674,"domain_scores_codex":[0.9853176,0.004967451,0.001825388,0.001139745,0.005936133,0.0008136071],"domain_scores_gemma":[0.9369935,0.03212932,0.00853852,0.003191659,0.01636697,0.002779984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.009447959,0.02471149,0.4308537,0.001467168,0.0006403319,0.0002313677,0.009040317,0.002080587,0.02039132,0.0006998561,0.004362381,0.4960735],"study_design_scores_gemma":[0.0001768057,0.01929142,0.9532633,0.0001117355,0.0001198841,0.0001057266,0.002259561,0.001883519,0.01977138,0.0004972067,0.002431936,0.00008747425],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9857137,0.000145735,0.006501492,0.00009444142,0.00006120691,0.002268341,0.0006215465,0.0001397804,0.004453777],"genre_scores_gemma":[0.9730094,0.0002617948,0.01423196,0.00007190686,0.00005542823,0.005780392,0.001104634,0.00006351194,0.005421009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.018548,"threshold_uncertainty_score":0.09809238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08720539950856393,"score_gpt":0.4465466292850784,"score_spread":0.3593412297765145,"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."}}