{"id":"W7061537676","doi":"","title":"Reading Comprehension Quiz Generation using Generative Pre-trained Transformers","year":2022,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Advanced Power Generation Technologies","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Summative assessment; Formative assessment; Transformer; Grading (engineering); Generative grammar; Reading comprehension; Generator (circuit theory)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007885722,0.0001619177,0.00021605,0.0002653214,0.0004884269,0.00001562606,0.0002224438,0.00007124477,0.000281176],"category_scores_gemma":[0.000005581732,0.0002261815,0.00008517314,0.0003434192,0.00008399775,0.0005578675,0.0001068132,0.0002042803,0.000004551443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002960407,"about_ca_system_score_gemma":0.00003319677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006005619,"about_ca_topic_score_gemma":0.00004163173,"domain_scores_codex":[0.9991297,0.00005412617,0.0001570266,0.0002069956,0.0002400609,0.0002121544],"domain_scores_gemma":[0.999589,0.00001888175,0.00007469896,0.0002014123,0.00007051898,0.00004549565],"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":[0.00003902164,0.00002184491,0.00006857559,0.00003932901,0.0000678935,0.00001331508,0.004323392,0.5238802,0.4536675,0.0004707606,0.001642492,0.01576567],"study_design_scores_gemma":[0.00162804,0.0002962344,0.0004829627,0.00003230737,0.00008854723,0.00003275393,0.01969755,0.8638916,0.07458103,0.0002099252,0.03834507,0.000713979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5963201,0.00007655482,0.4017843,0.0001678144,0.0003509184,0.0002309678,0.0001034124,0.0003850068,0.0005809746],"genre_scores_gemma":[0.9710718,0.00003232142,0.02848005,0.00004792386,0.00003323709,0.000001359599,0.0001347018,0.00002140559,0.0001772129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3790864,"threshold_uncertainty_score":0.9223413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02023307755512507,"score_gpt":0.2114350835525077,"score_spread":0.1912020059973827,"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."}}