{"id":"W7129293341","doi":"10.1109/waie67422.2025.11381152","title":"Evaluating an AI-powered Platform for Generating Instructional Materials on Mathematical Modelling of Direct Variation","year":2025,"lang":"","type":"article","venue":"","topic":"Mathematics Education and Teaching Techniques","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Stroke Network","funders":"","keywords":"CLARITY; Relevance (law); Curriculum; Variation (astronomy); Foundation (evidence); Range (aeronautics)","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":[0.01117894,0.001241438,0.000598822,0.001546953,0.0005257815,0.002647513,0.003070717,0.00143356,0.004657459],"category_scores_gemma":[0.05305335,0.0006329851,0.000762804,0.0009041827,0.001085577,0.003719895,0.002867735,0.001362235,0.001446442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001581633,"about_ca_system_score_gemma":0.002399043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001614425,"about_ca_topic_score_gemma":0.001849715,"domain_scores_codex":[0.992778,0.004045735,0.0006887604,0.0006961075,0.001463187,0.0003281456],"domain_scores_gemma":[0.9511358,0.03831531,0.001802089,0.003427535,0.004026294,0.001292898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004110941,0.01949822,0.02536552,0.005576241,0.0003213769,0.002029633,0.02359412,0.1330934,0.07555556,0.01326353,0.01035579,0.6872357],"study_design_scores_gemma":[0.005270841,0.03922504,0.0404041,0.001623313,0.0008507955,0.00130274,0.01186006,0.5752104,0.1968744,0.01697745,0.1096818,0.0007191072],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9073644,0.0001583306,0.07450396,0.000291451,0.0001050319,0.004177148,0.0004686593,0.004131341,0.008799778],"genre_scores_gemma":[0.5811224,0.0003022695,0.4071907,0.0002520806,0.00002982846,0.003956574,0.001861423,0.0006108312,0.00467396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01117894,"threshold_uncertainty_score":0.0591206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1870932252725949,"score_gpt":0.4540102245248826,"score_spread":0.2669169992522877,"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."}}