{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003823741,0.00173179,0.002128802,0.003305604,0.00073601,0.004069734,0.003187578,0.001864963,0.01392332],"category_scores_gemma":[0.01388301,0.001294229,0.002367716,0.005619506,0.001357767,0.009957287,0.002452202,0.003990862,0.004986988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002456484,"about_ca_system_score_gemma":0.002678056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004018049,"about_ca_topic_score_gemma":0.00398133,"domain_scores_codex":[0.9973477,0.0011053,0.0002689361,0.0003754607,0.0007739238,0.0001286792],"domain_scores_gemma":[0.9915336,0.006662169,0.0002284121,0.0008511955,0.0005921171,0.0001326866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001016968,0.0001955954,0.001502736,0.00400109,0.0002131361,0.0002072866,0.0004744066,0.03534489,0.0008583919,0.3995222,0.06235246,0.4952261],"study_design_scores_gemma":[0.00003105366,0.00007217356,0.0009476578,0.001297931,0.0001138517,0.0003919089,0.000178967,0.1386238,0.0007086273,0.564411,0.2931411,0.00008190153],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.005390149,0.2707404,0.676416,0.0111751,0.0009586585,0.0002132066,0.002322521,0.002697583,0.03008641],"genre_scores_gemma":[0.1224053,0.4507563,0.3913879,0.004373375,0.005264223,0.0009336737,0.008741168,0.001559869,0.01457825],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01392332,"threshold_uncertainty_score":0.04657811,"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."}}