{"id":"W2059210005","doi":"10.1145/944217.944243","title":"Evaluating modeling techniques based on models of learning","year":2003,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Domain (mathematical analysis); Grammar; Test (biology); Machine learning; Natural language processing; Mathematics; Linguistics","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":[0.009885469,0.001383438,0.0007227145,0.002944092,0.0004546456,0.003212603,0.001611952,0.002202166,0.002870468],"category_scores_gemma":[0.1186259,0.0004058849,0.001215198,0.001822334,0.000622226,0.007081771,0.002071537,0.001582971,0.0008482756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001472152,"about_ca_system_score_gemma":0.001607473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002645472,"about_ca_topic_score_gemma":0.003209576,"domain_scores_codex":[0.9886779,0.006962406,0.0006123111,0.0008776077,0.002692134,0.000177679],"domain_scores_gemma":[0.8659906,0.1148874,0.005097114,0.008254195,0.004940864,0.0008299336],"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":[0.003799654,0.006134857,0.04792151,0.002131129,0.002672653,0.0001748955,0.002655853,0.4176157,0.01751147,0.0243771,0.005071808,0.4699334],"study_design_scores_gemma":[0.0006537289,0.003389205,0.01230059,0.0003513906,0.0008901376,0.000219764,0.001009326,0.9317668,0.01435411,0.02806263,0.006845488,0.0001568587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6807297,0.001900265,0.299045,0.0006874647,0.0001394022,0.00104018,0.0008865726,0.002682045,0.01288933],"genre_scores_gemma":[0.8030939,0.0007313159,0.1920238,0.0001384357,0.00003153081,0.0005497893,0.001737929,0.0002873034,0.001406005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009885469,"threshold_uncertainty_score":0.05228001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1975873328404231,"score_gpt":0.372712511628928,"score_spread":0.1751251787885049,"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."}}