{"id":"W4309375705","doi":"10.1080/15305058.2022.2070755","title":"Generating reading comprehension items using automated processes","year":2022,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading comprehension; Blank; Comprehension; Computer science; Natural language processing; Test (biology); Reading (process); Artificial intelligence; Salient; Process (computing); Psychology; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005174801,0.0021493,0.001158099,0.003313177,0.0008187149,0.00189393,0.001901855,0.001229293,0.009178868],"category_scores_gemma":[0.03433377,0.0008219539,0.001469813,0.002132979,0.0008327854,0.002139599,0.002091763,0.001731563,0.006756426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006868548,"about_ca_system_score_gemma":0.001272682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001508119,"about_ca_topic_score_gemma":0.001922296,"domain_scores_codex":[0.9938393,0.002801723,0.0004933787,0.001828728,0.0009000025,0.0001368335],"domain_scores_gemma":[0.9609355,0.02903366,0.001308864,0.003726272,0.004781394,0.0002143193],"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":[0.0003477226,0.0006516719,0.008139097,0.0005188125,0.0001202471,0.0002916741,0.002671367,0.01173136,0.03431162,0.003541599,0.005421973,0.9322529],"study_design_scores_gemma":[0.0003609036,0.001169014,0.02351566,0.0001588897,0.0002569489,0.0008262675,0.001792656,0.791585,0.1268428,0.02796001,0.02530022,0.0002316466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03576569,0.00006690312,0.9465036,0.0001058673,0.00003910319,0.001096561,0.000802841,0.01396907,0.001650323],"genre_scores_gemma":[0.1217831,0.00006730525,0.8692374,0.00007398934,0.00004312238,0.002213731,0.003403415,0.0009616341,0.002216341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009178868,"threshold_uncertainty_score":0.03070641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08765853027184589,"score_gpt":0.3270988022823678,"score_spread":0.2394402720105219,"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."}}