{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003671421,0.0007508079,0.001016413,0.0005012092,0.0005745819,0.00496892,0.002283922,0.001955528,0.03988877],"category_scores_gemma":[0.02341809,0.0006715108,0.001215043,0.0006471564,0.002316896,0.01974539,0.002738707,0.005807651,0.009124141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001376542,"about_ca_system_score_gemma":0.002279906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003334394,"about_ca_topic_score_gemma":0.004909697,"domain_scores_codex":[0.9987161,0.0006725754,0.00003727013,0.0001613675,0.0003171023,0.00009562351],"domain_scores_gemma":[0.9776697,0.01769965,0.0003556949,0.002653578,0.0008836952,0.0007377426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002378379,0.0004391271,0.001388011,0.0004263771,0.00008249837,0.00007477868,0.000437105,0.01359448,0.0006373007,0.5919669,0.1248872,0.2658283],"study_design_scores_gemma":[0.00005207324,0.0000368332,0.0002033674,0.0001019915,0.00002029673,0.00004032702,0.0001336067,0.03548542,0.0005575989,0.9019212,0.06143024,0.00001696707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.02976651,0.01276334,0.6087668,0.1697446,0.002570679,0.0001037382,0.001810242,0.01035568,0.1641185],"genre_scores_gemma":[0.5462019,0.0129589,0.3018539,0.01593915,0.004144959,0.000412054,0.003712729,0.002063517,0.1127128],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.03988877,"threshold_uncertainty_score":0.1334412,"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."}}