{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003213333,0.00008806664,0.0001913199,0.0001715646,0.0001202004,0.00003665975,0.0000540392,0.00006246749,0.0009798219],"category_scores_gemma":[0.001022127,0.00007710525,0.00003543733,0.00008529607,0.00002132117,0.0003148082,0.00001452664,0.0004018415,0.00001146534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004478358,"about_ca_system_score_gemma":0.000258282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002951432,"about_ca_topic_score_gemma":0.000003610369,"domain_scores_codex":[0.9984155,0.0005075454,0.000380743,0.0001130856,0.0004712141,0.0001118894],"domain_scores_gemma":[0.9982314,0.0004179325,0.0006486784,0.00005876867,0.0006008206,0.00004245185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002803006,0.0000577457,0.7912233,0.00001890532,0.00007830328,5.818619e-8,0.05307696,0.0007609863,0.001092347,0.00005359342,0.00002542771,0.1535843],"study_design_scores_gemma":[0.001139634,0.0002750091,0.9553971,0.00009196435,0.00009084214,0.00001596353,0.03515541,0.001827936,0.0000202142,0.00003601445,0.005869504,0.00008040053],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926759,0.0005608379,0.00006758972,0.0001233987,0.0006425093,0.0001556864,1.554164e-7,0.000005990957,0.005767947],"genre_scores_gemma":[0.9951701,0.00002681318,0.0007813433,0.00006968217,0.0001134568,0.000005184207,0.000008703718,0.00001030643,0.003814476],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1641737,"threshold_uncertainty_score":0.9999334,"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."}}