{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007532577,0.001096465,0.0005698242,0.0006250768,0.0002055054,0.0008821784,0.001388392,0.0007766093,0.01333634],"category_scores_gemma":[0.005126393,0.0004286718,0.0007552106,0.0003422032,0.0003652436,0.0009871832,0.001077826,0.00134377,0.005306527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006050412,"about_ca_system_score_gemma":0.0006522202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001676749,"about_ca_topic_score_gemma":0.002106099,"domain_scores_codex":[0.9996711,0.00008537698,0.00002108337,0.000126311,0.00006427494,0.00003185028],"domain_scores_gemma":[0.9980577,0.001134423,0.00007099196,0.0002073112,0.0004686327,0.00006085917],"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":[0.0006814483,0.0004520243,0.00478756,0.0008200418,0.0001341875,0.000847073,0.000655119,0.2307419,0.05036261,0.009403852,0.02622345,0.6748907],"study_design_scores_gemma":[0.0001043887,0.000217398,0.00092673,0.0000386449,0.00003434452,0.0001572194,0.00006458467,0.9546144,0.02875108,0.007495297,0.007571888,0.00002407955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06988156,0.0003401417,0.8792841,0.0003040076,0.0002531933,0.0006287715,0.001546792,0.04092655,0.006834826],"genre_scores_gemma":[0.6618493,0.0002240717,0.3149634,0.0004060029,0.00005727702,0.001397423,0.005412313,0.002504674,0.01318553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01333634,"threshold_uncertainty_score":0.04461449,"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."}}