{"id":"W4412684241","doi":"10.1007/978-3-031-98281-1_14","title":"Leveraging LLMs for Bayesian and Deep Knowledge Tracing in the Logic-Muse Intelligent Tutoring System","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; Université Laval","funders":"","keywords":"Computer science; Tracing; Artificial intelligence; Bayesian network; Bayesian probability; Programming language","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":[0.00276413,0.0005465756,0.0006178041,0.00104446,0.0005112786,0.001013396,0.002526853,0.000251117,0.000001223934],"category_scores_gemma":[0.0001548206,0.0004206423,0.0001501565,0.0006404938,0.0001957723,0.0003918482,0.0008005643,0.0009318122,0.00000508035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006026391,"about_ca_system_score_gemma":0.0002955078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006923394,"about_ca_topic_score_gemma":0.00009980135,"domain_scores_codex":[0.9963915,0.0001130306,0.0007227524,0.001477341,0.0005343249,0.0007610978],"domain_scores_gemma":[0.9969518,0.001570951,0.0002701536,0.0009021672,0.0002117479,0.00009318668],"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":[0.000005639057,0.00002265671,0.0001117275,0.0005069362,0.00001591496,0.00007853423,0.01432617,0.03416593,0.00003128962,0.4092958,0.000004107801,0.5414353],"study_design_scores_gemma":[0.0002466136,0.000151124,0.00008189654,0.004579647,0.000014548,0.0001253128,0.0000362527,0.9684359,0.0004731003,0.01517496,0.00993266,0.0007479565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00006729518,0.001818474,0.9901215,0.0002691922,0.002590027,0.0008675259,0.000001179457,0.0001268664,0.004137893],"genre_scores_gemma":[0.8136616,0.00006842324,0.1830742,0.000527818,0.001027495,0.00007870719,0.000002370595,0.00004516495,0.001514277],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.93427,"threshold_uncertainty_score":0.9998245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02839351959529518,"score_gpt":0.2643871727330686,"score_spread":0.2359936531377734,"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."}}