{"id":"W4416366457","doi":"10.1109/tpami.2025.3634507","title":"Enhancing Mathematical Reasoning Through Autonomously Learning Knowledge","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Forgetting; Focus (optics); Cognition; Process (computing); Human intelligence; Knowledge representation and reasoning; Commonsense knowledge; Solver; Knowledge engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005350339,0.000283336,0.000461412,0.0005271789,0.0005444577,0.0002932284,0.0004663575,0.00009384421,0.0001007418],"category_scores_gemma":[0.00002425803,0.0002529628,0.0003067855,0.001320381,0.0000511145,0.0003044469,0.00001671387,0.0005972443,0.0001036008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008452264,"about_ca_system_score_gemma":0.00004836972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005647532,"about_ca_topic_score_gemma":0.000304047,"domain_scores_codex":[0.9980257,0.0001879051,0.0005575596,0.000663565,0.0002105679,0.0003547079],"domain_scores_gemma":[0.998882,0.0003535662,0.0001325071,0.0004372951,0.0001097801,0.00008483943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000109074,0.0003077581,0.0009540801,0.0001586566,0.00140891,0.00002258816,0.006020325,0.09181863,0.001106781,0.07152601,0.0000072905,0.8266581],"study_design_scores_gemma":[0.0001428432,0.0001913575,0.0003465647,0.0006263914,0.0006100166,0.00002281715,0.0006801335,0.6894161,0.3012325,0.001882478,0.004185974,0.0006628902],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001575041,0.0002939102,0.9948987,0.0001748015,0.0003172921,0.0001197333,0.000001831007,0.0002192545,0.002399407],"genre_scores_gemma":[0.9823452,0.0001118979,0.006522621,0.000154722,0.00002744444,0.0000262936,0.000001150907,0.0000127247,0.01079791],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9883761,"threshold_uncertainty_score":0.9999923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01789780073141665,"score_gpt":0.2860404762648374,"score_spread":0.2681426755334207,"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."}}