{"id":"W182355817","doi":"","title":"A Framework for Evaluating Semantic Knowledge in Problem-Solving- Based Intelligent Tutoring Systems","year":2008,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"","keywords":"Computer science; Procedural knowledge; Intelligent tutoring system; Knowledge-based systems; Artificial intelligence; Cognition; Semantic network; General knowledge; Descriptive knowledge; Natural language processing; Knowledge management","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01259525,0.0002641559,0.0003707994,0.000166358,0.001558698,0.0004444028,0.001752634,0.0001749993,0.000006253038],"category_scores_gemma":[0.000930302,0.0001953714,0.0003101242,0.001436305,0.0001857062,0.0003393346,0.0005450917,0.001567518,0.0000799761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006654838,"about_ca_system_score_gemma":0.0006990414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00043625,"about_ca_topic_score_gemma":0.000009517036,"domain_scores_codex":[0.9952062,0.0009625889,0.0006076883,0.0007233287,0.001239435,0.001260738],"domain_scores_gemma":[0.9942543,0.003607333,0.0001409034,0.0009301007,0.0009224192,0.00014498],"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":[0.00006050152,0.0003129126,0.004135528,0.001509587,0.0001784965,0.00003857707,0.09596661,0.08303516,0.002465971,0.8014637,0.005580673,0.005252267],"study_design_scores_gemma":[0.0003677383,0.000322553,0.0004709855,0.001454549,0.000005724179,0.00001851515,0.002658784,0.9673649,0.001452123,0.004171065,0.02137317,0.0003398899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03612312,0.001492707,0.9575756,0.0009298617,0.001393367,0.001882686,0.00000173173,0.0001848366,0.0004161345],"genre_scores_gemma":[0.9448069,0.00008255942,0.04830159,0.00008779085,0.001245836,0.0007690259,0.000002038459,0.0000516878,0.004652601],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.909274,"threshold_uncertainty_score":0.9997411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2264501416235463,"score_gpt":0.432506311255894,"score_spread":0.2060561696323477,"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."}}