{"id":"W7116141524","doi":"10.1007/s10489-025-07044-6","title":"CMCTS: A Constrained Monte Carlo Tree Search framework for mathematical reasoning in large language model","year":2025,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Monte Carlo tree search; Tree (set theory); Action (physics); Action selection; Monte Carlo method; Baseline (sea); Selection (genetic algorithm)","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":[0.0006892395,0.0001713679,0.0002684685,0.0001647702,0.00008646661,0.000109644,0.001002048,0.0001447647,0.00001074785],"category_scores_gemma":[0.0002502344,0.000169316,0.00006666858,0.0004748377,0.00005471148,0.0001177792,0.0003169668,0.0003467375,0.00002154523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008025848,"about_ca_system_score_gemma":0.0001414126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001898728,"about_ca_topic_score_gemma":0.00002149435,"domain_scores_codex":[0.998283,0.00002373589,0.0003975951,0.0005460214,0.0002251271,0.000524563],"domain_scores_gemma":[0.998619,0.0005045521,0.00004620566,0.0007053454,0.00005226715,0.00007267352],"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":[0.00001109384,0.00005110441,0.00002549048,0.0000599962,0.000008972163,0.000004731152,0.00401799,0.01776621,0.000314884,0.942957,0.00001780147,0.03476471],"study_design_scores_gemma":[0.0001112415,0.000009672824,0.000006172824,0.000146849,0.000003517685,0.000001409045,0.0008921505,0.7948279,0.00408685,0.1997702,0.0000184428,0.0001255936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01012679,0.0001392737,0.9791731,0.0003536151,0.00006428114,0.0005505843,0.000006996139,0.0001373158,0.009448027],"genre_scores_gemma":[0.5729083,0.000005148602,0.4265126,0.0002762866,0.00001545855,0.0001110031,7.618447e-7,0.000006942332,0.0001634568],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7770618,"threshold_uncertainty_score":0.6904507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02824518937086059,"score_gpt":0.3237130342735292,"score_spread":0.2954678449026686,"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."}}