{"id":"W7117259628","doi":"10.1145/3786333","title":"A Survey on Large Language Models for Mathematical Reasoning","year":2025,"lang":"en","type":"article","venue":"ACM Computing Surveys","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Cognition; Verbal reasoning; Automated reasoning; Psychology of reasoning; Reinforcement learning; Case-based reasoning; Language model; Qualitative reasoning","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":[0.007670151,0.0001849128,0.0003023991,0.0001387647,0.0002343448,0.0001878151,0.001549891,0.00008987577,0.000003239279],"category_scores_gemma":[0.002627731,0.0001781234,0.00009343091,0.0004046294,0.00001622967,0.0001462611,0.0008521155,0.0001905366,0.00002100309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005462463,"about_ca_system_score_gemma":0.00008642922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000143549,"about_ca_topic_score_gemma":0.00006846747,"domain_scores_codex":[0.997595,0.0007240226,0.0003574258,0.0005789144,0.0002350112,0.0005096176],"domain_scores_gemma":[0.9950814,0.003267724,0.00009037655,0.00136398,0.0001298797,0.00006665167],"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":[0.00001578495,0.0003310275,0.009784448,0.0001743784,0.0001100303,0.00001783209,0.003217257,0.03401551,0.00006538096,0.790833,0.003572186,0.1578632],"study_design_scores_gemma":[0.0004337631,0.00002707096,0.01344245,0.0001456598,0.000003669584,0.000001185507,0.00002426096,0.9589352,0.0001128454,0.02666256,0.00003990515,0.0001714445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07002319,0.00007799663,0.9269649,0.0002772991,0.0003843026,0.0002545396,0.0000136092,0.0003196646,0.001684513],"genre_scores_gemma":[0.8246873,6.506932e-7,0.1744083,0.0003984009,0.00005255436,0.000007299608,0.00001614579,0.00001312295,0.0004162276],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9249197,"threshold_uncertainty_score":0.726366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04404501978785593,"score_gpt":0.320547456125321,"score_spread":0.2765024363374651,"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."}}