{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002884775,0.001187671,0.000641768,0.002062967,0.0003214782,0.001798764,0.001286402,0.0007955207,0.008571384],"category_scores_gemma":[0.02511345,0.0004978523,0.0008321128,0.001232827,0.0003329142,0.002896593,0.001690983,0.0008385849,0.003819399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000520754,"about_ca_system_score_gemma":0.0007168832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001359273,"about_ca_topic_score_gemma":0.001838058,"domain_scores_codex":[0.997273,0.001388299,0.000310145,0.0005236345,0.0004245114,0.00008028856],"domain_scores_gemma":[0.9872714,0.008587195,0.0005099711,0.001365371,0.002020429,0.0002457183],"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":[0.001045596,0.0005025618,0.01598691,0.0006811723,0.0001447017,0.0005826881,0.003084545,0.02409746,0.04016727,0.005469442,0.01167971,0.8965579],"study_design_scores_gemma":[0.0002898469,0.0006519863,0.01289856,0.0001193955,0.0001309873,0.0007524031,0.001241709,0.8778957,0.07065073,0.01185296,0.02338322,0.0001324746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1067284,0.0001275557,0.8482456,0.0001174348,0.0001025213,0.0008557831,0.002273449,0.03776142,0.003787797],"genre_scores_gemma":[0.3964682,0.00009370769,0.5943442,0.00005144345,0.00002250783,0.001046879,0.004533636,0.001364277,0.002075128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008571384,"threshold_uncertainty_score":0.02867413,"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."}}