{"id":"W4379929879","doi":"10.21449/ijate.1249297","title":"Automatic item generation for online measurement and evaluation: Turkish literature items","year":2023,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Turkish; Computer science; Field (mathematics); Test (biology); Item bank; Item analysis; Subject-matter expert; Subject matter; Item response theory; Data science; Artificial intelligence; Statistics; Psychometrics; Curriculum; Expert system; Psychology; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.002475727,0.0001240839,0.0001566829,0.0007369982,0.00006557767,0.0003837192,0.0006010311,0.00008690094,0.0000132781],"category_scores_gemma":[0.0005618205,0.0001165462,0.0000640455,0.0004929319,0.00002178228,0.001251568,0.00007170073,0.0002096806,0.000001872758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006997156,"about_ca_system_score_gemma":0.001534626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002605087,"about_ca_topic_score_gemma":0.00001106591,"domain_scores_codex":[0.997789,0.0001225652,0.0006206944,0.0002351951,0.001092473,0.0001400181],"domain_scores_gemma":[0.9967818,0.0002382076,0.0004503503,0.0001832447,0.002292693,0.00005365008],"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":[0.000009323131,0.0009933664,0.008049111,0.00004219787,0.0001486852,0.000005961903,0.001018684,0.0007767601,0.004554612,0.05707783,0.01306203,0.9142615],"study_design_scores_gemma":[0.001914018,0.0002980874,0.425685,0.0008492951,0.00005199415,0.0001830826,0.001142137,0.5038887,0.0009414174,0.05187443,0.0128309,0.0003409823],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9239811,0.0009832768,0.03083363,0.03464446,0.008637823,0.0006587541,0.00001567209,0.00006538253,0.0001798576],"genre_scores_gemma":[0.9231015,0.0002850054,0.07509401,0.0003195088,0.0008397247,0.0001477727,0.0001521661,0.000008043725,0.00005222764],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9139205,"threshold_uncertainty_score":0.4752617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1047808688677508,"score_gpt":0.4375316124065066,"score_spread":0.3327507435387558,"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."}}