{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006068228,0.0006588688,0.0004162413,0.0003876213,0.0002855778,0.00108471,0.001713641,0.0009200444,0.002602735],"category_scores_gemma":[0.003451652,0.0003573816,0.0007077513,0.0003597401,0.000761533,0.00247403,0.001425472,0.00102,0.0005504985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003780023,"about_ca_system_score_gemma":0.0008377451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001010869,"about_ca_topic_score_gemma":0.001511626,"domain_scores_codex":[0.9997016,0.00006441834,0.00001788005,0.00007761218,0.0001100492,0.00002846525],"domain_scores_gemma":[0.9989893,0.0004969459,0.0001066219,0.0002385783,0.000128894,0.00003971715],"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":[0.0001907375,0.0004462199,0.001979745,0.0004582171,0.0001097193,0.0001733852,0.0004557583,0.4198784,0.06382646,0.05023228,0.002262887,0.4599862],"study_design_scores_gemma":[0.00003296472,0.0001114131,0.0002688705,0.00001470714,0.0000321128,0.00005992583,0.00003397771,0.9474626,0.02023036,0.02783835,0.003900156,0.0000146108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08735036,0.0002178407,0.9035376,0.0002994156,0.0000310965,0.00008502824,0.00004454182,0.002178897,0.006255074],"genre_scores_gemma":[0.5313227,0.0002939254,0.4656054,0.0001342662,0.00002110309,0.0001025304,0.0001486818,0.0001457696,0.002225488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002602735,"threshold_uncertainty_score":0.008706987,"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."}}