{"id":"W4412874171","doi":"10.1007/978-3-031-98459-4_5","title":"Math Education With Large Language Models: Peril or Promise?","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Mathematics education; Programming language; Theoretical computer science; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007341769,0.0005260151,0.0004635518,0.0008228536,0.0003319603,0.0007905732,0.003369744,0.0002576475,0.00003635058],"category_scores_gemma":[0.00009694516,0.0003960748,0.00008291051,0.001014747,0.0003714786,0.00118857,0.001102796,0.0006587168,0.00004633068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004406617,"about_ca_system_score_gemma":0.003259305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008788573,"about_ca_topic_score_gemma":0.0006163591,"domain_scores_codex":[0.9962003,0.00003652089,0.0004492427,0.001609345,0.0008788173,0.000825788],"domain_scores_gemma":[0.9972021,0.0002712497,0.0002354307,0.00172946,0.0003824422,0.0001793023],"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":[0.00002643741,0.0001051801,0.00001126753,0.0001012481,0.00001186187,0.0001152342,0.004074023,0.01448547,0.00003309255,0.3389749,0.00007460669,0.6419867],"study_design_scores_gemma":[0.0001431676,0.0002134961,0.00001102198,0.0007938481,0.00001177836,0.00007909794,0.000008044095,0.8493162,0.002028853,0.1437999,0.002879667,0.0007149172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001507727,0.0005117296,0.9779186,0.0008014411,0.001089724,0.00078548,0.000006576032,0.00023334,0.01850229],"genre_scores_gemma":[0.1603096,0.00009105293,0.8137011,0.005026375,0.0007143018,0.0001637943,0.00001586196,0.00007582555,0.01990205],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8348307,"threshold_uncertainty_score":0.9998491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01882941046336708,"score_gpt":0.272015009528283,"score_spread":0.2531855990649159,"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."}}