{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01328262,0.0007592005,0.001237363,0.0006577402,0.0008785449,0.006529762,0.00339228,0.003660991,0.03361367],"category_scores_gemma":[0.07093927,0.0005743142,0.0008333049,0.0006513964,0.003786101,0.02925694,0.004442992,0.006553555,0.008464119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175929,"about_ca_system_score_gemma":0.00323238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004827838,"about_ca_topic_score_gemma":0.006572822,"domain_scores_codex":[0.9962363,0.002493238,0.00008107749,0.0003659982,0.0005990605,0.0002244316],"domain_scores_gemma":[0.9208096,0.06475355,0.001063629,0.006599766,0.003440991,0.003332311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001423106,0.001376724,0.00909174,0.001113469,0.0002345133,0.0002046152,0.001123639,0.01278371,0.001005246,0.3573635,0.1250133,0.4892665],"study_design_scores_gemma":[0.0002790196,0.0003293616,0.001724879,0.0004205673,0.00008625441,0.0001881617,0.001230972,0.08809876,0.001236975,0.8255706,0.08076362,0.00007084209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.07050449,0.03173006,0.2049865,0.6071708,0.003630031,0.000119039,0.001477984,0.005729353,0.07465177],"genre_scores_gemma":[0.8079071,0.02174207,0.1137594,0.01903074,0.008473421,0.0003505705,0.001357435,0.0008076223,0.02657157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03361367,"threshold_uncertainty_score":0.112449,"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."}}