{"id":"W4309232742","doi":"10.21449/ijate.1124382","title":"Automatic story and item generation for reading comprehension assessments with transformers","year":2022,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University of Edmonton; University of Alberta","funders":"University of Alberta","keywords":"Fluency; Reading comprehension; Computer science; Comprehension; Literacy; Reading (process); Mathematics education; Multimedia; Psychology; Pedagogy; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009490437,0.00007957001,0.0001196194,0.0003330865,0.0001095193,0.0001701319,0.0003685057,0.0000178409,0.00001249419],"category_scores_gemma":[0.00003357241,0.00007575766,0.0000333531,0.0001047751,0.00001019134,0.001094772,0.00005216962,0.0001992505,1.040688e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008839525,"about_ca_system_score_gemma":0.0007870984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007716158,"about_ca_topic_score_gemma":0.000004812533,"domain_scores_codex":[0.998565,0.0001113318,0.0003559999,0.0001622726,0.0007102661,0.00009514389],"domain_scores_gemma":[0.9990141,0.0001750355,0.0003291685,0.0000906258,0.0003525012,0.00003859523],"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":[0.00004061078,0.0004935503,0.009560666,0.00002838621,0.00009814185,0.000008712844,0.001550437,0.0142667,0.007143974,0.02337877,0.0006650601,0.942765],"study_design_scores_gemma":[0.001399813,0.0004809715,0.02761747,0.0001177237,0.00001905245,0.0002372603,0.001593809,0.9626383,0.0002386332,0.001534221,0.003955268,0.0001674903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5404099,0.0000458636,0.4559708,0.001712163,0.001553854,0.0001671711,0.000001804413,0.000007893243,0.0001306011],"genre_scores_gemma":[0.8342242,0.00002074631,0.1652984,0.0002271676,0.0001374935,0.00004987362,0.00001149724,0.000005787927,0.00002478819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9483716,"threshold_uncertainty_score":0.3089308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04583102892320276,"score_gpt":0.3728767693014102,"score_spread":0.3270457403782074,"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."}}