{"id":"W4389254307","doi":"10.2139/ssrn.4641653","title":"Math Education with Large Language Models: Peril or Promise?","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs; University of Toronto; Fleming College","funders":"","keywords":"Mathematics education; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.001275303,0.0001188352,0.0001177648,0.0001414982,0.0002646108,0.0001948123,0.0004444233,0.00003594729,0.000007222196],"category_scores_gemma":[0.00002223203,0.00007839133,0.00004715942,0.0004011499,0.00000804946,0.0004946725,0.00005982699,0.000787152,0.00009372701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004061698,"about_ca_system_score_gemma":0.0027609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004451725,"about_ca_topic_score_gemma":0.0001346315,"domain_scores_codex":[0.9977619,0.00006595523,0.0001591629,0.00021394,0.000282741,0.001516272],"domain_scores_gemma":[0.9995019,0.00002152757,0.0001138553,0.0002063862,0.00008779504,0.00006854669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001715602,0.00003668481,0.0001240789,0.000008573916,0.00003665889,0.0000147348,0.002306169,0.0005656887,0.00005763606,0.9728149,0.00008536378,0.02393235],"study_design_scores_gemma":[0.003576004,0.003615084,0.002009851,0.001024224,0.00009024605,0.01006804,0.106454,0.3401408,0.0007905925,0.3347485,0.1951147,0.002368025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2136048,0.001178727,0.7802915,0.0007690625,0.0005979481,0.0002701081,8.497528e-7,0.0003570544,0.002929943],"genre_scores_gemma":[0.9103936,0.0002614459,0.0009555981,0.00006293917,0.000409182,0.0000246275,0.000001795664,0.00002068431,0.08787016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7793359,"threshold_uncertainty_score":0.4897718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01348118214342812,"score_gpt":0.2579260818050113,"score_spread":0.2444448996615832,"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."}}