{"id":"W4409992471","doi":"10.1109/iceit64364.2025.10975875","title":"Enhancing Contextual Understanding in AI-Powered Tutoring: Evaluating the Oliver System for Effective Learning Support","year":2025,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Human–computer interaction","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":[0.003676725,0.0002153146,0.0003245926,0.0002304291,0.000633046,0.0003726868,0.0005487851,0.00008620197,0.000005187429],"category_scores_gemma":[0.0006395116,0.0001618264,0.0001175335,0.0005305929,0.0000315338,0.0003657098,0.0002289573,0.0004396369,0.00001375761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001029434,"about_ca_system_score_gemma":0.0001981118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001554708,"about_ca_topic_score_gemma":0.00004805531,"domain_scores_codex":[0.9976788,0.0004170874,0.0005405741,0.0005302952,0.0003127868,0.000520477],"domain_scores_gemma":[0.9976187,0.00165113,0.0001866061,0.0002978449,0.0002025475,0.00004321902],"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":[0.00002836408,0.00001265931,0.002191295,0.0001633022,0.00005515786,0.000007014763,0.004208886,0.003870868,0.004781444,0.9793846,0.00003168721,0.005264711],"study_design_scores_gemma":[0.004776173,0.002313711,0.004023779,0.005994856,0.0001015774,0.00005690768,0.09891324,0.7862817,0.06021693,0.004577508,0.03119411,0.001549504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01390371,0.00008489404,0.9710176,0.0002276098,0.001516704,0.001065447,3.005929e-7,0.0002503201,0.0119334],"genre_scores_gemma":[0.985386,9.806936e-7,0.001908898,0.0001105093,0.0001160701,0.0001688362,9.592883e-7,0.00001416091,0.01229364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9748071,"threshold_uncertainty_score":0.6599091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04928074131484046,"score_gpt":0.3347340421036759,"score_spread":0.2854533007888355,"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."}}