{"id":"W6949516502","doi":"10.5281/zenodo.15174917","title":"Intrinsic and Contextual Factors Impacting Student Ratings of Automatically Generated Questions: A Large-Scale Data Analysis","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nutrasource","funders":"","keywords":"Formative assessment; Set (abstract data type); Key (lock); Data set; Code (set theory); Student life","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":[0.001140228,0.00010732,0.0002125888,0.0003664783,0.001041053,0.0008044909,0.001255787,0.00003858445,0.0002086466],"category_scores_gemma":[0.000980673,0.0001000071,0.00003770697,0.001195015,0.00005720138,0.0003817817,0.002342953,0.0001794768,0.00005952834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006881775,"about_ca_system_score_gemma":0.000008518552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005706738,"about_ca_topic_score_gemma":0.000001843656,"domain_scores_codex":[0.9983786,0.000365888,0.0003408323,0.000417273,0.000268357,0.0002290522],"domain_scores_gemma":[0.9985278,0.00007655645,0.0001540989,0.0006242261,0.0005369955,0.00008038237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005581033,0.0008942675,0.00621568,0.0004104796,0.002636415,0.00002903507,0.04161972,0.00230086,0.02128068,0.6903724,0.01373558,0.220449],"study_design_scores_gemma":[0.001333314,0.0005453894,0.102967,0.0004346405,0.0003503124,0.00003558714,0.008880127,0.2806825,0.00237913,0.0002803211,0.6014373,0.0006744043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2449961,0.0001250284,0.7491785,0.0002369057,0.00008842428,0.0002754978,0.0000726032,0.0005072578,0.004519672],"genre_scores_gemma":[0.9959022,0.00001474396,0.003073354,0.00003527818,0.0000255103,2.440749e-8,0.0002204141,0.00008780605,0.000640674],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7509061,"threshold_uncertainty_score":0.8007039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04051850945371471,"score_gpt":0.3008131794880423,"score_spread":0.2602946700343276,"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."}}