{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009903752,0.0004760306,0.0006224689,0.001814005,0.0004829662,0.001235733,0.0005773536,0.0006602498,0.001016305],"category_scores_gemma":[0.06883755,0.0002280681,0.0005344024,0.002110516,0.0006563056,0.0009763695,0.00139738,0.0009683541,0.0007070919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004073449,"about_ca_system_score_gemma":0.0004030084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001306466,"about_ca_topic_score_gemma":0.002282504,"domain_scores_codex":[0.9880908,0.006548496,0.001093259,0.001558298,0.002301267,0.0004080086],"domain_scores_gemma":[0.8493637,0.1213283,0.01030684,0.007181509,0.01012625,0.001693468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001327868,0.00120518,0.852362,0.0007348901,0.0003605412,0.0002453102,0.0119042,0.003613646,0.01501854,0.000366651,0.002861338,0.11],"study_design_scores_gemma":[0.00004039364,0.0009968347,0.9684002,0.00004188098,0.0001013723,0.0002202516,0.002159411,0.01594076,0.00848342,0.0004071989,0.003144414,0.00006378163],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9914905,0.0001097017,0.005782617,0.00005538932,0.000009410936,0.0002053103,0.001654765,0.0001292899,0.0005628935],"genre_scores_gemma":[0.9885435,0.00005068379,0.00702068,0.00002736486,0.00001471478,0.0004274543,0.003352332,0.00004599469,0.0005172224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009903752,"threshold_uncertainty_score":0.05237669,"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."}}