{"id":"W6911924949","doi":"10.5281/zenodo.15174916","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":"Innovative Teaching Methods","field":"Social Sciences","cited_by":1,"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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00483138,0.00009764853,0.0002242992,0.0004339052,0.002512111,0.0005274872,0.0008976675,0.00005817958,0.001278864],"category_scores_gemma":[0.008083195,0.00009636858,0.00003183755,0.002265762,0.0003103837,0.0003038643,0.001328495,0.0002408501,0.00003573507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001445819,"about_ca_system_score_gemma":0.00002041155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003273856,"about_ca_topic_score_gemma":0.00003081049,"domain_scores_codex":[0.9969072,0.001781421,0.0003407523,0.0003409073,0.0003610631,0.0002686198],"domain_scores_gemma":[0.9983128,0.0001903624,0.0001681519,0.0004274834,0.0008143331,0.00008691682],"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":[0.00013725,0.001282268,0.01683715,0.0002427715,0.002778362,0.00001153994,0.2068479,0.0001369003,0.02460039,0.4032907,0.03965361,0.3041811],"study_design_scores_gemma":[0.001966801,0.0003743337,0.2705783,0.0002264482,0.0008246801,0.00000595183,0.09168739,0.01180789,0.001202369,0.00141429,0.6191816,0.000729973],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8498464,0.00007458444,0.09941355,0.0008854361,0.00008437459,0.0005093166,0.0002942829,0.0006189974,0.04827312],"genre_scores_gemma":[0.9936306,0.00002264899,0.005193974,0.00006726767,0.00003705516,2.539637e-8,0.0005534973,0.0001244234,0.0003704587],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.579528,"threshold_uncertainty_score":0.9996341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07529076081770007,"score_gpt":0.394601401563918,"score_spread":0.319310640746218,"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."}}