{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005836127,0.00008139356,0.0001218105,0.0002385512,0.00025172,0.0002066044,0.001026543,0.00001432867,0.00001000299],"category_scores_gemma":[0.0008040593,0.00008133123,0.00004064087,0.0003241671,0.000009164601,0.0005792496,0.0005216599,0.0002393366,8.539359e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002125641,"about_ca_system_score_gemma":0.0002556347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003755361,"about_ca_topic_score_gemma":5.010996e-7,"domain_scores_codex":[0.9983812,0.00007503158,0.0005051853,0.0001486182,0.0007517376,0.0001382308],"domain_scores_gemma":[0.9980558,0.0002993034,0.000641939,0.0001052889,0.0008513174,0.00004632199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000436297,0.000032477,0.004015476,0.000009547412,0.00003194614,0.0002113772,0.0005286653,0.8961634,0.08403037,0.0002903775,0.00008881987,0.0145932],"study_design_scores_gemma":[0.0002036134,0.00004610876,0.0001191007,0.0001097485,0.000004221023,0.002254932,0.00008168027,0.995644,0.0009228606,0.0003159241,0.0002148079,0.00008295094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5951998,0.0001362838,0.4025631,0.0002968126,0.001492475,0.00003197676,0.000001009492,0.0001196556,0.0001588438],"genre_scores_gemma":[0.665902,8.532843e-7,0.3336343,0.0001611511,0.0002849828,7.930742e-7,4.941603e-7,0.000005806623,0.000009656284],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09948067,"threshold_uncertainty_score":0.3316591,"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."}}